Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.7055. Min Act: -0.1700
Data Index: 2283896 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.5493. Min Act: -0.1700
Data Index: 8132366 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.5493. Min Act: -0.1700
Data Index: 4589705 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.5180. Min Act: -0.1700
Data Index: 6462997 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.4868. Min Act: -0.1700
Data Index: 5491429 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.4555. Min Act: -0.1700
Data Index: 5756123 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.4243. Min Act: -0.1700
Data Index: 1106905 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.4243. Min Act: -0.1700
Data Index: 7268494 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.4243. Min Act: -0.1700
Data Index: 118640 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.3930. Min Act: -0.1700
Data Index: 889519 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.3618. Min Act: -0.1700
Data Index: 6569643 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.3618. Min Act: -0.1700
Data Index: 830151 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.3305. Min Act: -0.1700
Data Index: 2045640 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.3618. Min Act: -0.1700
Data Index: 3593800 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.3618. Min Act: -0.1700
Data Index: 5101467 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.3618. Min Act: -0.1700
Data Index: 4137056 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.3305. Min Act: -0.1700
Data Index: 6364007 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.3305. Min Act: -0.1700
Data Index: 3921714 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.2993. Min Act: -0.1700
Data Index: 4041048 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7055. Min Range: -6.7055
Max Act: 6.2993. Min Act: -0.1700
Data Index: 5512235 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19