Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.6035. Min Act: -0.1700
Data Index: 3858365 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.5723. Min Act: -0.1700
Data Index: 6024270 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.4160. Min Act: -0.1700
Data Index: 4929488 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.3535. Min Act: -0.1700
Data Index: 7437705 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.2910. Min Act: -0.1700
Data Index: 5400332 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.2598. Min Act: -0.1700
Data Index: 5952909 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.2598. Min Act: -0.1700
Data Index: 7627510 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.2598. Min Act: -0.1700
Data Index: 6531596 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.2285. Min Act: -0.1700
Data Index: 7151888 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.2285. Min Act: -0.1700
Data Index: 8692223 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.1973. Min Act: -0.1700
Data Index: 4285257 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.2285. Min Act: -0.1700
Data Index: 7534483 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.1660. Min Act: -0.1700
Data Index: 6750069 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.1660. Min Act: -0.1700
Data Index: 4845017 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.1660. Min Act: -0.1700
Data Index: 1854959 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.1348. Min Act: -0.1700
Data Index: 195610 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.1348. Min Act: -0.1700
Data Index: 2902143 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.1035. Min Act: -0.1700
Data Index: 2695586 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.1348. Min Act: -0.1700
Data Index: 6678646 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6035. Min Range: -5.6035
Max Act: 5.1035. Min Act: -0.1700
Data Index: 3333637 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19