Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1041. Min Range: -9.1041
Max Act: 9.1041. Min Act: -0.1700
Data Index: 532744 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1041. Min Range: -9.1041
Max Act: 9.0416. Min Act: -0.1700
Data Index: 6838441 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.8541. Min Act: -0.1700
Data Index: 2617177 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.9166. Min Act: -0.1700
Data Index: 8504853 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.7916. Min Act: -0.1700
Data Index: 8650557 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.7291. Min Act: -0.1700
Data Index: 4701004 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.6666. Min Act: -0.1700
Data Index: 3917114 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.6041. Min Act: -0.1700
Data Index: 3355133 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.5416. Min Act: -0.1700
Data Index: 4215356 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.4791. Min Act: -0.1700
Data Index: 2206964 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.4166. Min Act: -0.1700
Data Index: 2780253 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.4166. Min Act: -0.1700
Data Index: 1196162 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.3541. Min Act: -0.1700
Data Index: 5603744 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.3541. Min Act: -0.1700
Data Index: 2052015 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.3541. Min Act: -0.1700
Data Index: 767363 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.2916. Min Act: -0.1700
Data Index: 2576803 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.2603. Min Act: -0.1700
Data Index: 466459 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.2603. Min Act: -0.1700
Data Index: 6228529 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.1978. Min Act: -0.1700
Data Index: 2778039 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1041. Min Range: -9.1041
Max Act: 8.2291. Min Act: -0.1700
Data Index: 2198366 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19