Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3661 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.7409. Min Act: -0.1700
Data Index: 6925217 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.6784. Min Act: -0.1700
Data Index: 1837473 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.5847. Min Act: -0.1700
Data Index: 7612734 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.4597. Min Act: -0.1700
Data Index: 7456540 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.4284. Min Act: -0.1700
Data Index: 8000293 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.3659. Min Act: -0.1700
Data Index: 2097242 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.3034. Min Act: -0.1700
Data Index: 3183823 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.3659. Min Act: -0.1700
Data Index: 1142728 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.3347. Min Act: -0.1700
Data Index: 3856086 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.2722. Min Act: -0.1700
Data Index: 1447649 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.2409. Min Act: -0.1700
Data Index: 2829377 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.2409. Min Act: -0.1700
Data Index: 2836602 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.2409. Min Act: -0.1700
Data Index: 6007970 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.2409. Min Act: -0.1700
Data Index: 5317122 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.2097. Min Act: -0.1700
Data Index: 7953030 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.1784. Min Act: -0.1700
Data Index: 8470425 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.1784. Min Act: -0.1700
Data Index: 137312 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.1472. Min Act: -0.1700
Data Index: 1749289 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.1159. Min Act: -0.1700
Data Index: 78196 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7409. Min Range: -7.7409
Max Act: 7.1472. Min Act: -0.1700
Data Index: 2094696 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19