Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3109 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3420. Min Range: -4.3420
Max Act: 4.3420. Min Act: -0.1700
Data Index: 7847250 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3420. Min Range: -4.3420
Max Act: 4.0919. Min Act: -0.1700
Data Index: 7333449 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3420. Min Range: -4.3420
Max Act: 4.0919. Min Act: -0.1700
Data Index: 5208074 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3420. Min Range: -4.3420
Max Act: 4.0294. Min Act: -0.1700
Data Index: 2902409 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.9981. Min Act: -0.1700
Data Index: 8629014 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.9044. Min Act: -0.1700
Data Index: 8315271 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.9044. Min Act: -0.1700
Data Index: 3694210 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8731. Min Act: -0.1700
Data Index: 7105991 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8731. Min Act: -0.1700
Data Index: 7968852 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8731. Min Act: -0.1700
Data Index: 3065993 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8731. Min Act: -0.1700
Data Index: 1215912 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8418. Min Act: -0.1700
Data Index: 5828117 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8418. Min Act: -0.1700
Data Index: 17056 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8418. Min Act: -0.1700
Data Index: 2720460 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8418. Min Act: -0.1700
Data Index: 3350772 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8105. Min Act: -0.1700
Data Index: 4894773 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8105. Min Act: -0.1700
Data Index: 3558336 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.8105. Min Act: -0.1700
Data Index: 8359033 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.7480. Min Act: -0.1700
Data Index: 6565413 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3420. Min Range: -4.3420
Max Act: 3.7480. Min Act: -0.1700
Data Index: 4382587 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19