Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1203 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0416. Min Range: -6.0416
Max Act: 6.0416. Min Act: -0.1699
Data Index: 7129976 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.8541. Min Act: -0.1700
Data Index: 349774 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.8541. Min Act: -0.1700
Data Index: 5634489 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.7916. Min Act: -0.1700
Data Index: 7595196 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.7603. Min Act: -0.1700
Data Index: 383375 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.7291. Min Act: -0.1700
Data Index: 8165543 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.6666. Min Act: -0.1700
Data Index: 2836632 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.6666. Min Act: -0.1700
Data Index: 3810170 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.6353. Min Act: -0.1700
Data Index: 6531619 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.6041. Min Act: -0.1700
Data Index: 8488035 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.6041. Min Act: -0.1700
Data Index: 7949637 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.5416. Min Act: -0.1700
Data Index: 6936584 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.5728. Min Act: -0.1700
Data Index: 5112547 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.5728. Min Act: -0.1700
Data Index: 151929 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.5416. Min Act: -0.1700
Data Index: 1414682 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.5103. Min Act: -0.1700
Data Index: 7315991 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.5416. Min Act: -0.1700
Data Index: 1993092 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.5416. Min Act: -0.1700
Data Index: 4458777 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.5416. Min Act: -0.1700
Data Index: 3861085 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.5103. Min Act: -0.1700
Data Index: 6995912 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19