Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2177 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.3321. Min Act: -0.1700
Data Index: 1494999 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.2696. Min Act: -0.1700
Data Index: 2826014 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.2696. Min Act: -0.1700
Data Index: 8477993 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.1759. Min Act: -0.1700
Data Index: 2348790 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.1134. Min Act: -0.1700
Data Index: 3802195 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.0821. Min Act: -0.1700
Data Index: 7185027 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.0821. Min Act: -0.1700
Data Index: 2729253 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.0821. Min Act: -0.1700
Data Index: 1251014 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.0508. Min Act: -0.1700
Data Index: 4754192 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.0508. Min Act: -0.1700
Data Index: 7909208 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3321. Min Range: -4.3321
Max Act: 4.0196. Min Act: -0.1700
Data Index: 2498181 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3321. Min Range: -4.3321
Max Act: 3.9883. Min Act: -0.1700
Data Index: 1637130 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3321. Min Range: -4.3321
Max Act: 3.9883. Min Act: -0.1700
Data Index: 6272369 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3321. Min Range: -4.3321
Max Act: 3.9883. Min Act: -0.1700
Data Index: 8368683 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3321. Min Range: -4.3321
Max Act: 3.9571. Min Act: -0.1700
Data Index: 4446791 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3321. Min Range: -4.3321
Max Act: 3.9571. Min Act: -0.1700
Data Index: 8741249 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3321. Min Range: -4.3321
Max Act: 3.9571. Min Act: -0.1700
Data Index: 195893 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3321. Min Range: -4.3321
Max Act: 3.9258. Min Act: -0.1700
Data Index: 7668421 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3321. Min Range: -4.3321
Max Act: 3.9258. Min Act: -0.1700
Data Index: 2258259 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3321. Min Range: -4.3321
Max Act: 3.9258. Min Act: -0.1700
Data Index: 3678754 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19