Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6384 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.7409. Min Act: -0.1700
Data Index: 7255059 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.4284. Min Act: -0.1700
Data Index: 2714117 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.1784. Min Act: -0.1700
Data Index: 8121839 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.1784. Min Act: -0.1700
Data Index: 6551235 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.1784. Min Act: -0.1700
Data Index: 4988844 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.1472. Min Act: -0.1700
Data Index: 3458298 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.1159. Min Act: -0.1700
Data Index: 2372217 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.1159. Min Act: -0.1700
Data Index: 2534144 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.0847. Min Act: -0.1700
Data Index: 8202350 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.0534. Min Act: -0.1700
Data Index: 4113078 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7409. Min Range: -6.7409
Max Act: 5.9909. Min Act: -0.1700
Data Index: 4412976 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7409. Min Range: -6.7409
Max Act: 6.0222. Min Act: -0.1700
Data Index: 5075565 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7409. Min Range: -6.7409
Max Act: 5.9909. Min Act: -0.1700
Data Index: 8552475 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7409. Min Range: -6.7409
Max Act: 5.9909. Min Act: -0.1700
Data Index: 381024 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7409. Min Range: -6.7409
Max Act: 5.9597. Min Act: -0.1700
Data Index: 5942111 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7409. Min Range: -6.7409
Max Act: 5.9597. Min Act: -0.1700
Data Index: 8696644 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7409. Min Range: -6.7409
Max Act: 5.9597. Min Act: -0.1700
Data Index: 8825337 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7409. Min Range: -6.7409
Max Act: 5.9284. Min Act: -0.1700
Data Index: 381023 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7409. Min Range: -6.7409
Max Act: 5.9597. Min Act: -0.1700
Data Index: 7624081 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7409. Min Range: -6.7409
Max Act: 5.9597. Min Act: -0.1700
Data Index: 7378580 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19