Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2749 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0545. Min Range: -7.0545
Max Act: 7.0545. Min Act: -0.1700
Data Index: 7850332 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.9607. Min Act: -0.1700
Data Index: 5649882 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.6170. Min Act: -0.1700
Data Index: 3910265 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.5857. Min Act: -0.1700
Data Index: 4767282 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.5232. Min Act: -0.1700
Data Index: 6838445 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.5232. Min Act: -0.1700
Data Index: 8737127 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.4607. Min Act: -0.1700
Data Index: 7224878 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.4607. Min Act: -0.1700
Data Index: 5105575 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.3670. Min Act: -0.1700
Data Index: 1560497 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.3982. Min Act: -0.1700
Data Index: 7218819 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.3982. Min Act: -0.1700
Data Index: 5551510 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.3670. Min Act: -0.1700
Data Index: 5422975 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.3670. Min Act: -0.1700
Data Index: 3833015 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.3670. Min Act: -0.1700
Data Index: 3186669 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.3045. Min Act: -0.1700
Data Index: 8577527 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.3045. Min Act: -0.1700
Data Index: 672679 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.3045. Min Act: -0.1700
Data Index: 1931507 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.2107. Min Act: -0.1700
Data Index: 1606226 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.2420. Min Act: -0.1700
Data Index: 1827239 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0545. Min Range: -7.0545
Max Act: 6.2420. Min Act: -0.1700
Data Index: 1656083 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19