Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 284 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0770. Min Range: -6.0770
Max Act: 6.0770. Min Act: -0.1700
Data Index: 4627536 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0770. Min Range: -6.0770
Max Act: 6.0145. Min Act: -0.1700
Data Index: 3169783 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.9833. Min Act: -0.1700
Data Index: 7267898 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.9520. Min Act: -0.1700
Data Index: 5086174 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.9520. Min Act: -0.1700
Data Index: 5477045 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.8895. Min Act: -0.1700
Data Index: 1889584 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.8895. Min Act: -0.1700
Data Index: 2379388 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.8270. Min Act: -0.1700
Data Index: 1334095 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.8583. Min Act: -0.1700
Data Index: 6665292 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.8270. Min Act: -0.1700
Data Index: 2760892 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.8270. Min Act: -0.1700
Data Index: 5972056 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.7958. Min Act: -0.1700
Data Index: 6793696 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.7958. Min Act: -0.1700
Data Index: 7398515 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.7958. Min Act: -0.1700
Data Index: 1180560 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.7333. Min Act: -0.1700
Data Index: 3112833 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.7333. Min Act: -0.1700
Data Index: 6653181 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.7333. Min Act: -0.1700
Data Index: 3245652 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.7333. Min Act: -0.1700
Data Index: 5166724 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.7020. Min Act: -0.1700
Data Index: 1129135 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0770. Min Range: -6.0770
Max Act: 5.7020. Min Act: -0.1700
Data Index: 5751091 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19