Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3599 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0969. Min Act: -0.1700
Data Index: 8602697 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0969. Min Act: -0.1700
Data Index: 5607176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0653. Min Act: -0.1700
Data Index: 3041090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0338. Min Act: -0.1700
Data Index: 1695770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0496. Min Act: -0.1700
Data Index: 3347633 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0496. Min Act: -0.1700
Data Index: 3692752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0338. Min Act: -0.1700
Data Index: 8553839 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0338. Min Act: -0.1700
Data Index: 3106620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0338. Min Act: -0.1700
Data Index: 6632738 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0338. Min Act: -0.1700
Data Index: 5685181 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0338. Min Act: -0.1700
Data Index: 2689671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0022. Min Act: -0.1700
Data Index: 4281580 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0969. Min Range: -3.0969
Max Act: 2.9864. Min Act: -0.1700
Data Index: 509641 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0969. Min Range: -3.0969
Max Act: 3.0022. Min Act: -0.1700
Data Index: 3478879 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0969. Min Range: -3.0969
Max Act: 2.9706. Min Act: -0.1700
Data Index: 1897204 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0969. Min Range: -3.0969
Max Act: 2.9706. Min Act: -0.1700
Data Index: 8050212 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0969. Min Range: -3.0969
Max Act: 2.9547. Min Act: -0.1700
Data Index: 8559817 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0969. Min Range: -3.0969
Max Act: 2.9547. Min Act: -0.1700
Data Index: 3865657 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0969. Min Range: -3.0969
Max Act: 2.9231. Min Act: -0.1700
Data Index: 7205613 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0969. Min Range: -3.0969
Max Act: 2.9072. Min Act: -0.1700
Data Index: 442845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19