Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4250 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3622. Min Range: -9.3622
Max Act: 9.3622. Min Act: -0.1700
Data Index: 8253266 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3622. Min Range: -9.3622
Max Act: 9.2372. Min Act: -0.1700
Data Index: 3201405 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3622. Min Range: -9.3622
Max Act: 9.1747. Min Act: -0.1700
Data Index: 2888158 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3622. Min Range: -9.3622
Max Act: 9.1747. Min Act: -0.1700
Data Index: 1640286 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.9872. Min Act: -0.1700
Data Index: 3828642 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.9247. Min Act: -0.1700
Data Index: 5727960 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.9247. Min Act: -0.1700
Data Index: 1108556 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.9247. Min Act: -0.1700
Data Index: 6145311 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.8622. Min Act: -0.1700
Data Index: 3793335 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.7372. Min Act: -0.1700
Data Index: 5446092 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.7372. Min Act: -0.1700
Data Index: 6397373 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.6747. Min Act: -0.1700
Data Index: 7038354 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.6747. Min Act: -0.1700
Data Index: 3066162 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.7372. Min Act: -0.1700
Data Index: 4025541 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.6747. Min Act: -0.1700
Data Index: 4615201 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.6747. Min Act: -0.1700
Data Index: 4158058 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.6747. Min Act: -0.1700
Data Index: 5247929 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.6122. Min Act: -0.1700
Data Index: 5441943 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.6122. Min Act: -0.1700
Data Index: 6990701 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3622. Min Range: -9.3622
Max Act: 8.6122. Min Act: -0.1700
Data Index: 3102370 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19