Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4638 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.9219. Min Act: -0.1700
Data Index: 3953839 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.8744. Min Act: -0.1700
Data Index: 5529468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.8267. Min Act: -0.1700
Data Index: 752268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.8108. Min Act: -0.1700
Data Index: 1924492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7949. Min Act: -0.1700
Data Index: 3827554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7630. Min Act: -0.1700
Data Index: 7428464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7630. Min Act: -0.1700
Data Index: 3931517 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7630. Min Act: -0.1700
Data Index: 6038211 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7630. Min Act: -0.1700
Data Index: 5702468 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7470. Min Act: -0.1700
Data Index: 1153716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7470. Min Act: -0.1700
Data Index: 5351836 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7311. Min Act: -0.1700
Data Index: 2208584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7311. Min Act: -0.1700
Data Index: 3648814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7151. Min Act: -0.1700
Data Index: 5812885 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.6991. Min Act: -0.1700
Data Index: 1223710 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.7151. Min Act: -0.1700
Data Index: 3984830 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.6831. Min Act: -0.1700
Data Index: 3126948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.6670. Min Act: -0.1700
Data Index: 2405435 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.6670. Min Act: -0.1700
Data Index: 5887144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9219. Min Range: -2.9219
Max Act: 2.6670. Min Act: -0.1700
Data Index: 2367531 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19