Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3990 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.9737. Min Act: -0.1700
Data Index: 4104840 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.8799. Min Act: -0.1700
Data Index: 1723881 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.8487. Min Act: -0.1700
Data Index: 4477750 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.8174. Min Act: -0.1700
Data Index: 1787747 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7549. Min Act: -0.1700
Data Index: 3459214 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7862. Min Act: -0.1700
Data Index: 716240 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7549. Min Act: -0.1700
Data Index: 949579 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7237. Min Act: -0.1700
Data Index: 3656213 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6924. Min Act: -0.1700
Data Index: 8338911 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6924. Min Act: -0.1700
Data Index: 5347455 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6924. Min Act: -0.1700
Data Index: 1119370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6924. Min Act: -0.1700
Data Index: 4567044 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6924. Min Act: -0.1700
Data Index: 4499720 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6924. Min Act: -0.1700
Data Index: 2397092 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6924. Min Act: -0.1700
Data Index: 7070439 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6612. Min Act: -0.1700
Data Index: 4489336 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6612. Min Act: -0.1700
Data Index: 4584338 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6612. Min Act: -0.1700
Data Index: 5332643 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6612. Min Act: -0.1700
Data Index: 3429954 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6299. Min Act: -0.1700
Data Index: 5666546 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19