Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3661 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9226. Min Range: -8.9226
Max Act: 8.9226. Min Act: -0.1700
Data Index: 8006196 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.6726. Min Act: -0.1700
Data Index: 186537 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9226. Min Range: -8.9226
Max Act: 8.4226. Min Act: -0.1700
Data Index: 7344008 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9226. Min Range: -8.9226
Max Act: 8.2976. Min Act: -0.1700
Data Index: 5805387 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9226. Min Range: -8.9226
Max Act: 8.1726. Min Act: -0.1698
Data Index: 4044958 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9226. Min Range: -8.9226
Max Act: 8.1101. Min Act: -0.1700
Data Index: 7314390 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.4226. Min Act: -0.1700
Data Index: 1401260 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.8601. Min Act: -0.1700
Data Index: 28423 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.2039. Min Act: -0.1700
Data Index: 6080891 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9226. Min Range: -8.9226
Max Act: 8.2351. Min Act: -0.1700
Data Index: 7367603 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.0164. Min Act: -0.1700
Data Index: 5426542 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.7976. Min Act: -0.1700
Data Index: 6361319 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.6101. Min Act: -0.1700
Data Index: 105998 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.7351. Min Act: -0.1700
Data Index: 6986132 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.1101. Min Act: -0.1700
Data Index: 387018 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.4226. Min Act: -0.1700
Data Index: 7726238 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.7976. Min Act: -0.1700
Data Index: 8315746 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.5476. Min Act: -0.1700
Data Index: 2201043 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.6726. Min Act: -0.1700
Data Index: 2792032 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9226. Min Range: -8.9226
Max Act: 7.5476. Min Act: -0.1700
Data Index: 2330335 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19