Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 526 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1047. Min Range: -7.1047
Max Act: 7.1047. Min Act: -0.1700
Data Index: 5735788 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1047. Min Range: -7.1047
Max Act: 7.0422. Min Act: -0.1700
Data Index: 3299236 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1047. Min Range: -7.1047
Max Act: 7.0110. Min Act: -0.1700
Data Index: 1407856 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.9485. Min Act: -0.1700
Data Index: 522860 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.9485. Min Act: -0.1700
Data Index: 4909816 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.9172. Min Act: -0.1700
Data Index: 3235374 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.9172. Min Act: -0.1700
Data Index: 6373076 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.9172. Min Act: -0.1700
Data Index: 239143 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.8860. Min Act: -0.1700
Data Index: 8198684 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.8860. Min Act: -0.1700
Data Index: 7295317 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.8235. Min Act: -0.1700
Data Index: 5917657 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.8547. Min Act: -0.1700
Data Index: 5246820 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.8235. Min Act: -0.1700
Data Index: 3315363 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.7922. Min Act: -0.1700
Data Index: 4263795 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.7297. Min Act: -0.1700
Data Index: 2823091 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.7297. Min Act: -0.1700
Data Index: 4721577 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.7297. Min Act: -0.1700
Data Index: 306508 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.7297. Min Act: -0.1700
Data Index: 2388677 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.7297. Min Act: -0.1700
Data Index: 2258528 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1047. Min Range: -7.1047
Max Act: 6.6672. Min Act: -0.1700
Data Index: 2320027 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19