Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 471 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.7598. Min Act: -0.1700
Data Index: 2421616 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.6035. Min Act: -0.1700
Data Index: 1364849 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.5098. Min Act: -0.1700
Data Index: 522349 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.5098. Min Act: -0.1700
Data Index: 1593624 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.4785. Min Act: -0.1700
Data Index: 4268190 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.4473. Min Act: -0.1700
Data Index: 7118095 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.3535. Min Act: -0.1700
Data Index: 3988508 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.2910. Min Act: -0.1700
Data Index: 1034924 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.2910. Min Act: -0.1700
Data Index: 734784 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.2910. Min Act: -0.1700
Data Index: 4610495 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.2598. Min Act: -0.1700
Data Index: 7668329 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.2598. Min Act: -0.1700
Data Index: 7578945 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.2598. Min Act: -0.1700
Data Index: 4300666 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.2285. Min Act: -0.1700
Data Index: 8692494 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.2285. Min Act: -0.1700
Data Index: 4166329 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.1973. Min Act: -0.1700
Data Index: 3462755 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.1973. Min Act: -0.1700
Data Index: 6600553 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.1973. Min Act: -0.1700
Data Index: 7277013 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.1973. Min Act: -0.1700
Data Index: 3941238 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7598. Min Range: -5.7598
Max Act: 5.1660. Min Act: -0.1700
Data Index: 1379945 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19