Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1802 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.7884. Min Act: -0.1700
Data Index: 5030703 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.7884. Min Act: -0.1700
Data Index: 8160455 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.7572. Min Act: -0.1700
Data Index: 2753643 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.7415. Min Act: -0.1700
Data Index: 182014 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.7415. Min Act: -0.1700
Data Index: 8799324 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.7259. Min Act: -0.1700
Data Index: 3351436 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.6790. Min Act: -0.1700
Data Index: 1877529 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.6633. Min Act: -0.1700
Data Index: 28788 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.6477. Min Act: -0.1700
Data Index: 967459 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.6477. Min Act: -0.1700
Data Index: 5611936 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.6320. Min Act: -0.1700
Data Index: 427387 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.6164. Min Act: -0.1700
Data Index: 2564247 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.6007. Min Act: -0.1700
Data Index: 1016403 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.6164. Min Act: -0.1700
Data Index: 313290 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.6007. Min Act: -0.1700
Data Index: 3813784 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.5851. Min Act: -0.1700
Data Index: 6616347 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.5851. Min Act: -0.1700
Data Index: 8022231 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.5851. Min Act: -0.1700
Data Index: 8025530 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.5851. Min Act: -0.1700
Data Index: 7162161 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7884. Min Range: -3.7884
Max Act: 3.5694. Min Act: -0.1700
Data Index: 4546903 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19