Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3165 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.7754. Min Act: -0.1700
Data Index: 8801821 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.6504. Min Act: -0.1700
Data Index: 2899921 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.5879. Min Act: -0.1700
Data Index: 600701 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.5879. Min Act: -0.1700
Data Index: 2161344 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.5254. Min Act: -0.1700
Data Index: 8217863 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.5567. Min Act: -0.1700
Data Index: 8493976 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.5254. Min Act: -0.1700
Data Index: 2833726 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.5567. Min Act: -0.1700
Data Index: 2549122 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.5254. Min Act: -0.1700
Data Index: 3457535 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.5567. Min Act: -0.1700
Data Index: 6205288 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.5254. Min Act: -0.1700
Data Index: 2231595 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.4942. Min Act: -0.1700
Data Index: 324262 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.4629. Min Act: -0.1700
Data Index: 6234318 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.4942. Min Act: -0.1700
Data Index: 4956992 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.4942. Min Act: -0.1700
Data Index: 4360507 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.4942. Min Act: -0.1700
Data Index: 4354893 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.4942. Min Act: -0.1700
Data Index: 4079707 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.4629. Min Act: -0.1700
Data Index: 6348986 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.4629. Min Act: -0.1700
Data Index: 1653921 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7754. Min Range: -4.7754
Max Act: 4.4629. Min Act: -0.1700
Data Index: 3577411 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19