Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7307. Min Range: -6.7307
Max Act: 6.7307. Min Act: -0.1700
Data Index: 84122 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7307. Min Range: -6.7307
Max Act: 6.6994. Min Act: -0.1700
Data Index: 2641362 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7307. Min Range: -6.7307
Max Act: 6.3869. Min Act: -0.1700
Data Index: 2019393 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7307. Min Range: -6.7307
Max Act: 6.2307. Min Act: -0.1700
Data Index: 6866198 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7307. Min Range: -6.7307
Max Act: 6.1682. Min Act: -0.1700
Data Index: 1037308 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7307. Min Range: -6.7307
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5797526 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7307. Min Range: -6.7307
Max Act: 6.0432. Min Act: -0.1700
Data Index: 8305013 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.9494. Min Act: -0.1700
Data Index: 331943 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.9182. Min Act: -0.1700
Data Index: 7136277 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.9182. Min Act: -0.1700
Data Index: 2603290 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.9182. Min Act: -0.1700
Data Index: 3777449 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.8869. Min Act: -0.1700
Data Index: 798573 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.8557. Min Act: -0.1700
Data Index: 5791307 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.8244. Min Act: -0.1700
Data Index: 4621848 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.8244. Min Act: -0.1700
Data Index: 5616020 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.8244. Min Act: -0.1700
Data Index: 6591915 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.7932. Min Act: -0.1700
Data Index: 1918443 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.7307. Min Act: -0.1700
Data Index: 3032854 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.6994. Min Act: -0.1700
Data Index: 3012091 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7307. Min Range: -6.7307
Max Act: 5.6994. Min Act: -0.1700
Data Index: 2533592 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19