Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5054 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.8084. Min Act: -0.1700
Data Index: 8803599 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.7286. Min Act: -0.1700
Data Index: 1601691 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6806. Min Act: -0.1700
Data Index: 6481676 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6806. Min Act: -0.1700
Data Index: 616500 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6646. Min Act: -0.1700
Data Index: 4847292 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6806. Min Act: -0.1700
Data Index: 4990505 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6646. Min Act: -0.1700
Data Index: 2836262 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6486. Min Act: -0.1700
Data Index: 3303660 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6325. Min Act: -0.1700
Data Index: 2811626 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6486. Min Act: -0.1700
Data Index: 6722207 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6325. Min Act: -0.1700
Data Index: 7960686 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6325. Min Act: -0.1700
Data Index: 2847491 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6164. Min Act: -0.1700
Data Index: 2010659 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6164. Min Act: -0.1700
Data Index: 631465 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6164. Min Act: -0.1700
Data Index: 5060513 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6164. Min Act: -0.1700
Data Index: 4091257 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6325. Min Act: -0.1700
Data Index: 7166099 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6003. Min Act: -0.1700
Data Index: 1379997 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6003. Min Act: -0.1700
Data Index: 6304952 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8084. Min Range: -2.8084
Max Act: 2.6003. Min Act: -0.1700
Data Index: 1826261 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19