Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2402 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8845. Min Act: -0.1700
Data Index: 5004607 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8845. Min Act: -0.1700
Data Index: 5155984 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8845. Min Act: -0.1700
Data Index: 1001795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8532. Min Act: -0.1700
Data Index: 7478705 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8532. Min Act: -0.1700
Data Index: 7598918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8532. Min Act: -0.1700
Data Index: 5896257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8532. Min Act: -0.1700
Data Index: 109540 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8532. Min Act: -0.1700
Data Index: 4987604 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8532. Min Act: -0.1700
Data Index: 2924769 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8532. Min Act: -0.1700
Data Index: 1987264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8532. Min Act: -0.1700
Data Index: 282352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8532. Min Act: -0.1700
Data Index: 2801941 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.7907. Min Act: -0.1700
Data Index: 1150383 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8219. Min Act: -0.1700
Data Index: 5608489 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8219. Min Act: -0.1700
Data Index: 2848332 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8219. Min Act: -0.1700
Data Index: 2743344 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8219. Min Act: -0.1700
Data Index: 5457189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8219. Min Act: -0.1700
Data Index: 677369 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8219. Min Act: -0.1700
Data Index: 4797953 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8845. Min Range: -3.8845
Max Act: 3.8219. Min Act: -0.1700
Data Index: 3891144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19