Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.8860. Min Act: -0.1700
Data Index: 3250355 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.6985. Min Act: -0.1700
Data Index: 5911624 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.6985. Min Act: -0.1700
Data Index: 288048 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.5735. Min Act: -0.1700
Data Index: 4400063 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.5735. Min Act: -0.1700
Data Index: 4362235 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.5110. Min Act: -0.1700
Data Index: 3922126 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.5110. Min Act: -0.1700
Data Index: 5911625 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.5110. Min Act: -0.1700
Data Index: 5920715 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.4485. Min Act: -0.1700
Data Index: 5492577 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.4485. Min Act: -0.1700
Data Index: 4362233 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.3860. Min Act: -0.1700
Data Index: 4169873 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.3860. Min Act: -0.1700
Data Index: 5492578 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.3235. Min Act: -0.1700
Data Index: 4400064 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.3235. Min Act: -0.1700
Data Index: 3250356 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.2610. Min Act: -0.1700
Data Index: 4417577 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.2610. Min Act: -0.1700
Data Index: 288049 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.1985. Min Act: -0.1700
Data Index: 1562774 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.1985. Min Act: -0.1700
Data Index: 491136 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.2610. Min Act: -0.1700
Data Index: 3415674 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8860. Min Range: -9.8860
Max Act: 9.1985. Min Act: -0.1700
Data Index: 3507796 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19