Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.9095. Min Act: -0.1700
Data Index: 7482658 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.8158. Min Act: -0.1700
Data Index: 3986627 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.7220. Min Act: -0.1700
Data Index: 8482876 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.6283. Min Act: -0.1700
Data Index: 6133866 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.5970. Min Act: -0.1700
Data Index: 2499424 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.5970. Min Act: -0.1700
Data Index: 6161031 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.5658. Min Act: -0.1700
Data Index: 394134 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.4720. Min Act: -0.1700
Data Index: 7070942 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.5033. Min Act: -0.1700
Data Index: 1188415 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.5033. Min Act: -0.1700
Data Index: 4768121 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.5033. Min Act: -0.1700
Data Index: 4397818 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.5033. Min Act: -0.1700
Data Index: 6619006 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.4720. Min Act: -0.1700
Data Index: 8029757 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.4720. Min Act: -0.1700
Data Index: 5861649 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.4408. Min Act: -0.1700
Data Index: 7472298 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.4408. Min Act: -0.1700
Data Index: 672420 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.4095. Min Act: -0.1700
Data Index: 1029121 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.3783. Min Act: -0.1700
Data Index: 5510165 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.4095. Min Act: -0.1700
Data Index: 7081513 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9095. Min Range: -4.9095
Max Act: 4.4408. Min Act: -0.1700
Data Index: 2538377 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19