Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.6426. Min Act: -0.1700
Data Index: 1745442 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.4864. Min Act: -0.1700
Data Index: 3105239 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.4864. Min Act: -0.1700
Data Index: 8673631 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.3926. Min Act: -0.1700
Data Index: 2666183 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.3926. Min Act: -0.1700
Data Index: 3952391 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.3926. Min Act: -0.1700
Data Index: 5167540 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.3926. Min Act: -0.1700
Data Index: 798473 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.3301. Min Act: -0.1700
Data Index: 5818306 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.2676. Min Act: -0.1700
Data Index: 5551819 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.2364. Min Act: -0.1700
Data Index: 7049118 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.2676. Min Act: -0.1700
Data Index: 4731806 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.2364. Min Act: -0.1700
Data Index: 6215630 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.2364. Min Act: -0.1700
Data Index: 778300 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.2051. Min Act: -0.1700
Data Index: 7695235 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.2364. Min Act: -0.1700
Data Index: 6108610 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.2051. Min Act: -0.1700
Data Index: 4494812 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.1739. Min Act: -0.1700
Data Index: 903098 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.1426. Min Act: -0.1700
Data Index: 200209 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.1739. Min Act: -0.1700
Data Index: 610143 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6426. Min Range: -6.6426
Max Act: 6.1739. Min Act: -0.1700
Data Index: 2866086 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19