Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 817 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.8876. Min Act: -0.1700
Data Index: 1597025 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.9501. Min Act: -0.1700
Data Index: 8192811 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.7626. Min Act: -0.1700
Data Index: 1111339 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.3876. Min Act: -0.1700
Data Index: 1549627 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.4501. Min Act: -0.1700
Data Index: 8333093 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.4501. Min Act: -0.1700
Data Index: 7315146 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.3876. Min Act: -0.1700
Data Index: 3661462 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.3251. Min Act: -0.1700
Data Index: 7363361 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.2626. Min Act: -0.1700
Data Index: 5763757 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.2626. Min Act: -0.1700
Data Index: 6640855 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.2001. Min Act: -0.1700
Data Index: 1098260 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.2001. Min Act: -0.1700
Data Index: 5000626 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.2001. Min Act: -0.1700
Data Index: 8429592 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.2001. Min Act: -0.1700
Data Index: 6812822 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.1376. Min Act: -0.1700
Data Index: 2151617 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.1376. Min Act: -0.1700
Data Index: 7899429 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.1376. Min Act: -0.1700
Data Index: 2559499 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.1376. Min Act: -0.1700
Data Index: 2161144 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.1376. Min Act: -0.1700
Data Index: 2511150 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9501. Min Range: -12.9501
Max Act: 12.0751. Min Act: -0.1700
Data Index: 5653355 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19