Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3219 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1857. Min Range: -7.1857
Max Act: 7.1857. Min Act: -0.1700
Data Index: 6998885 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1857. Min Range: -7.1857
Max Act: 7.0919. Min Act: -0.1700
Data Index: 8109364 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.9982. Min Act: -0.1700
Data Index: 8499516 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.9357. Min Act: -0.1700
Data Index: 1529283 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.9357. Min Act: -0.1700
Data Index: 22928 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.8732. Min Act: -0.1700
Data Index: 6276286 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.8732. Min Act: -0.1700
Data Index: 6174589 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.8107. Min Act: -0.1700
Data Index: 2864767 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.7482. Min Act: -0.1700
Data Index: 4063576 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.6857. Min Act: -0.1700
Data Index: 816461 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.6857. Min Act: -0.1700
Data Index: 1690589 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.6857. Min Act: -0.1700
Data Index: 7182498 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.6857. Min Act: -0.1700
Data Index: 6178809 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.6544. Min Act: -0.1700
Data Index: 5515054 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.6544. Min Act: -0.1700
Data Index: 2495191 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.6544. Min Act: -0.1700
Data Index: 6720001 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.6544. Min Act: -0.1700
Data Index: 5765810 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.6232. Min Act: -0.1700
Data Index: 2474703 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.6232. Min Act: -0.1700
Data Index: 4565273 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1857. Min Range: -7.1857
Max Act: 6.5919. Min Act: -0.1700
Data Index: 2788229 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19