Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4927 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0729. Min Range: -6.0729
Max Act: 6.0729. Min Act: -0.1700
Data Index: 4657029 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0729. Min Range: -6.0729
Max Act: 6.0729. Min Act: -0.1700
Data Index: 5353198 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0729. Min Range: -6.0729
Max Act: 6.0104. Min Act: -0.1700
Data Index: 360139 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.9479. Min Act: -0.1700
Data Index: 74727 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.8229. Min Act: -0.1700
Data Index: 8224050 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7604. Min Act: -0.1700
Data Index: 4890548 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.7292. Min Act: -0.1700
Data Index: 5744194 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.6979. Min Act: -0.1700
Data Index: 134192 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.6354. Min Act: -0.1700
Data Index: 6129409 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.6042. Min Act: -0.1700
Data Index: 6692114 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.6042. Min Act: -0.1700
Data Index: 6412672 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.5104. Min Act: -0.1700
Data Index: 4457586 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.4792. Min Act: -0.1700
Data Index: 6437715 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.4792. Min Act: -0.1700
Data Index: 5146266 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.4479. Min Act: -0.1700
Data Index: 2868220 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.4792. Min Act: -0.1700
Data Index: 2693086 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.4479. Min Act: -0.1700
Data Index: 1173969 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.4479. Min Act: -0.1700
Data Index: 723938 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.4479. Min Act: -0.1700
Data Index: 1899334 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0729. Min Range: -6.0729
Max Act: 5.4479. Min Act: -0.1700
Data Index: 855298 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19