Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.8132. Min Act: -0.1700
Data Index: 875534 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.7195. Min Act: -0.1700
Data Index: 1664276 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6570. Min Act: -0.1700
Data Index: 6199052 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.5945. Min Act: -0.1700
Data Index: 2618887 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.5320. Min Act: -0.1700
Data Index: 6511324 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.5320. Min Act: -0.1700
Data Index: 6837819 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.5320. Min Act: -0.1700
Data Index: 5742418 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.5007. Min Act: -0.1700
Data Index: 3064066 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.5007. Min Act: -0.1700
Data Index: 1978267 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.4695. Min Act: -0.1700
Data Index: 1818263 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.5007. Min Act: -0.1700
Data Index: 111211 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.5007. Min Act: -0.1700
Data Index: 6837821 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.4695. Min Act: -0.1700
Data Index: 994741 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.4695. Min Act: -0.1700
Data Index: 4358029 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.4382. Min Act: -0.1700
Data Index: 8283220 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.4695. Min Act: -0.1700
Data Index: 1972399 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.4695. Min Act: -0.1700
Data Index: 3523455 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.4695. Min Act: -0.1700
Data Index: 211839 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.4382. Min Act: -0.1700
Data Index: 1524762 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.4382. Min Act: -0.1700
Data Index: 866881 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19