Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1936 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1390. Min Range: -6.1390
Max Act: 6.1390. Min Act: -0.1700
Data Index: 6657960 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1390. Min Range: -6.1390
Max Act: 6.1390. Min Act: -0.1700
Data Index: 6501742 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1390. Min Range: -6.1390
Max Act: 6.0140. Min Act: -0.1700
Data Index: 49549 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.9515. Min Act: -0.1700
Data Index: 6943589 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.9515. Min Act: -0.1700
Data Index: 5747185 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8890. Min Act: -0.1700
Data Index: 4038720 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8890. Min Act: -0.1700
Data Index: 2474605 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8578. Min Act: -0.1700
Data Index: 5545836 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8265. Min Act: -0.1700
Data Index: 3857814 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8578. Min Act: -0.1700
Data Index: 2651660 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8265. Min Act: -0.1700
Data Index: 6804094 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7953. Min Act: -0.1700
Data Index: 3019117 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8265. Min Act: -0.1700
Data Index: 8572166 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8265. Min Act: -0.1700
Data Index: 4080595 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.8265. Min Act: -0.1700
Data Index: 7784590 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7953. Min Act: -0.1700
Data Index: 4423146 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7953. Min Act: -0.1700
Data Index: 4262091 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7953. Min Act: -0.1700
Data Index: 3667160 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7640. Min Act: -0.1700
Data Index: 3631028 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1390. Min Range: -6.1390
Max Act: 5.7953. Min Act: -0.1700
Data Index: 1507622 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19