Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 611 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.3551. Min Act: -0.1700
Data Index: 1966600 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.3864. Min Act: -0.1700
Data Index: 4652164 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.3551. Min Act: -0.1700
Data Index: 1244163 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.3239. Min Act: -0.1700
Data Index: 1622407 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.3239. Min Act: -0.1700
Data Index: 7027479 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.3239. Min Act: -0.1700
Data Index: 8582340 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.3239. Min Act: -0.1700
Data Index: 4423510 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.2926. Min Act: -0.1700
Data Index: 5094588 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.2614. Min Act: -0.1700
Data Index: 3257184 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.2614. Min Act: -0.1700
Data Index: 551372 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.2614. Min Act: -0.1700
Data Index: 4586596 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.2301. Min Act: -0.1700
Data Index: 2593131 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.2301. Min Act: -0.1700
Data Index: 8388056 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.1989. Min Act: -0.1700
Data Index: 7855314 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.1989. Min Act: -0.1700
Data Index: 969249 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.1989. Min Act: -0.1700
Data Index: 7268670 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.1989. Min Act: -0.1700
Data Index: 5814920 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.1989. Min Act: -0.1700
Data Index: 1429705 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.1989. Min Act: -0.1700
Data Index: 3218687 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3864. Min Range: -6.3864
Max Act: 6.1989. Min Act: -0.1700
Data Index: 3514450 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19