Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 791 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0104. Min Range: -7.0104
Max Act: 7.0104. Min Act: -0.1700
Data Index: 438497 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.8229. Min Act: -0.1700
Data Index: 1362114 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.3854. Min Act: -0.1700
Data Index: 5936909 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.4166. Min Act: -0.1700
Data Index: 4303152 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.4166. Min Act: -0.1700
Data Index: 6466306 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.4166. Min Act: -0.1700
Data Index: 394031 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.3229. Min Act: -0.1700
Data Index: 2822346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.2916. Min Act: -0.1700
Data Index: 5204565 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.2604. Min Act: -0.1700
Data Index: 5932915 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.2291. Min Act: -0.1700
Data Index: 50158 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 728015 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 2078059 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.2291. Min Act: -0.1700
Data Index: 509109 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.1666. Min Act: -0.1700
Data Index: 1856340 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.1666. Min Act: -0.1700
Data Index: 5140651 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 4415640 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.1354. Min Act: -0.1700
Data Index: 8336219 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.1354. Min Act: -0.1700
Data Index: 6823040 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.1041. Min Act: -0.1700
Data Index: 4367064 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0104. Min Range: -7.0104
Max Act: 6.0729. Min Act: -0.1700
Data Index: 3345061 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19