Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5612 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1337. Min Range: -4.1337
Max Act: 4.1337. Min Act: -0.1700
Data Index: 7908056 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1337. Min Range: -4.1337
Max Act: 4.1024. Min Act: -0.1700
Data Index: 3355104 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1337. Min Range: -4.1337
Max Act: 4.0712. Min Act: -0.1700
Data Index: 1010501 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.9148. Min Act: -0.1700
Data Index: 1864320 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.9461. Min Act: -0.1700
Data Index: 8145447 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.9148. Min Act: -0.1700
Data Index: 3502508 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.8836. Min Act: -0.1700
Data Index: 585800 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.8836. Min Act: -0.1700
Data Index: 3038080 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.8523. Min Act: -0.1700
Data Index: 3414157 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.8210. Min Act: -0.1700
Data Index: 8329654 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.7898. Min Act: -0.1700
Data Index: 5418580 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.7898. Min Act: -0.1700
Data Index: 6346503 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.7898. Min Act: -0.1700
Data Index: 3173926 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.7898. Min Act: -0.1700
Data Index: 6655501 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.7898. Min Act: -0.1700
Data Index: 8426551 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.7898. Min Act: -0.1700
Data Index: 2439386 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.7898. Min Act: -0.1700
Data Index: 5804076 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.7585. Min Act: -0.1700
Data Index: 77798 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.7585. Min Act: -0.1700
Data Index: 3281288 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1337. Min Range: -4.1337
Max Act: 3.7585. Min Act: -0.1700
Data Index: 7302526 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19