Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1764 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.7829. Min Act: -0.1700
Data Index: 8595971 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.7516. Min Act: -0.1700
Data Index: 5668851 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.7203. Min Act: -0.1700
Data Index: 3466683 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6891. Min Act: -0.1700
Data Index: 431546 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6891. Min Act: -0.1700
Data Index: 63520 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6578. Min Act: -0.1700
Data Index: 8333913 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6578. Min Act: -0.1700
Data Index: 7347349 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6578. Min Act: -0.1700
Data Index: 6221758 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6578. Min Act: -0.1700
Data Index: 5632741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6578. Min Act: -0.1700
Data Index: 8707666 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6578. Min Act: -0.1700
Data Index: 8344873 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6578. Min Act: -0.1700
Data Index: 5297494 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6578. Min Act: -0.1700
Data Index: 8112714 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6265. Min Act: -0.1700
Data Index: 5788192 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6265. Min Act: -0.1700
Data Index: 6488206 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6265. Min Act: -0.1700
Data Index: 6790522 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6265. Min Act: -0.1700
Data Index: 982857 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6265. Min Act: -0.1700
Data Index: 7437363 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6265. Min Act: -0.1700
Data Index: 7682433 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7829. Min Range: -3.7829
Max Act: 3.6265. Min Act: -0.1700
Data Index: 7716297 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19