Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5827 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.8136. Min Act: -0.1700
Data Index: 4194789 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.8136. Min Act: -0.1700
Data Index: 6040305 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.6886. Min Act: -0.1700
Data Index: 2641977 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.6886. Min Act: -0.1700
Data Index: 797644 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.5948. Min Act: -0.1700
Data Index: 5582188 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.5636. Min Act: -0.1700
Data Index: 3269871 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.5323. Min Act: -0.1700
Data Index: 8663698 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.5323. Min Act: -0.1700
Data Index: 8111892 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.5323. Min Act: -0.1700
Data Index: 4185631 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.5323. Min Act: -0.1700
Data Index: 790103 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.4386. Min Act: -0.1700
Data Index: 2850827 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.4386. Min Act: -0.1700
Data Index: 7590527 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.4073. Min Act: -0.1700
Data Index: 2712612 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.4073. Min Act: -0.1700
Data Index: 7786039 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.4073. Min Act: -0.1700
Data Index: 7347588 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.4073. Min Act: -0.1700
Data Index: 6542626 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.4073. Min Act: -0.1700
Data Index: 5717816 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.4073. Min Act: -0.1700
Data Index: 3237908 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.3761. Min Act: -0.1700
Data Index: 7834319 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8136. Min Range: -5.8136
Max Act: 5.3761. Min Act: -0.1700
Data Index: 8234201 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19