Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 515 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3929. Min Range: -11.3929
Max Act: 11.3929. Min Act: -0.1700
Data Index: 2083007 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3929. Min Range: -11.3929
Max Act: 11.3304. Min Act: -0.1700
Data Index: 4221600 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3929. Min Range: -11.3929
Max Act: 11.2679. Min Act: -0.1700
Data Index: 2499579 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3929. Min Range: -11.3929
Max Act: 11.2679. Min Act: -0.1700
Data Index: 7111198 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3929. Min Range: -11.3929
Max Act: 11.1429. Min Act: -0.1700
Data Index: 3086786 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3929. Min Range: -11.3929
Max Act: 11.0804. Min Act: -0.1700
Data Index: 358543 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3929. Min Range: -11.3929
Max Act: 11.0179. Min Act: -0.1700
Data Index: 2498995 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3929. Min Range: -11.3929
Max Act: 11.0179. Min Act: -0.1700
Data Index: 7205971 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.9554. Min Act: -0.1700
Data Index: 4303245 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.8929. Min Act: -0.1700
Data Index: 7335039 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.9554. Min Act: -0.1700
Data Index: 1544529 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3929. Min Range: -11.3929
Max Act: 11.0179. Min Act: -0.1700
Data Index: 2440571 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.8929. Min Act: -0.1700
Data Index: 7861160 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.8304. Min Act: -0.1700
Data Index: 1566597 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.8304. Min Act: -0.1700
Data Index: 2405621 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.8304. Min Act: -0.1700
Data Index: 1039999 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.8304. Min Act: -0.1700
Data Index: 7207560 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.8304. Min Act: -0.1700
Data Index: 122943 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.8929. Min Act: -0.1700
Data Index: 1860872 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3929. Min Range: -11.3929
Max Act: 10.8304. Min Act: -0.1700
Data Index: 3584496 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19