Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4926 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5411. Min Range: -6.5411
Max Act: 6.5411. Min Act: -0.1700
Data Index: 8388652 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5411. Min Range: -6.5411
Max Act: 6.4161. Min Act: -0.1700
Data Index: 2531309 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5411. Min Range: -6.5411
Max Act: 6.3848. Min Act: -0.1700
Data Index: 5047587 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5411. Min Range: -6.5411
Max Act: 6.2286. Min Act: -0.1700
Data Index: 4393185 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5411. Min Range: -6.5411
Max Act: 6.1036. Min Act: -0.1700
Data Index: 8586234 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5411. Min Range: -6.5411
Max Act: 6.1036. Min Act: -0.1700
Data Index: 4428284 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5411. Min Range: -6.5411
Max Act: 6.0411. Min Act: -0.1700
Data Index: 8730390 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5411. Min Range: -6.5411
Max Act: 6.0411. Min Act: -0.1700
Data Index: 2439813 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5411. Min Range: -6.5411
Max Act: 6.0098. Min Act: -0.1700
Data Index: 4875622 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.9786. Min Act: -0.1700
Data Index: 607754 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.9786. Min Act: -0.1700
Data Index: 7995143 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.9161. Min Act: -0.1700
Data Index: 3987618 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.9473. Min Act: -0.1700
Data Index: 1229596 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.9473. Min Act: -0.1700
Data Index: 2598560 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.9473. Min Act: -0.1700
Data Index: 2420171 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.8223. Min Act: -0.1700
Data Index: 486365 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.8536. Min Act: -0.1700
Data Index: 4507890 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.8536. Min Act: -0.1700
Data Index: 3841628 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.8223. Min Act: -0.1700
Data Index: 3134466 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5411. Min Range: -6.5411
Max Act: 5.7911. Min Act: -0.1700
Data Index: 1141179 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19