Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.4520. Min Act: -0.1700
Data Index: 4798493 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.4364. Min Act: -0.1700
Data Index: 7094186 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.3893. Min Act: -0.1700
Data Index: 5719000 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.3580. Min Act: -0.1700
Data Index: 8302809 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.3737. Min Act: -0.1700
Data Index: 2712872 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.3580. Min Act: -0.1700
Data Index: 4839349 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.3266. Min Act: -0.1700
Data Index: 3018782 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.3266. Min Act: -0.1700
Data Index: 6843613 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.2952. Min Act: -0.1700
Data Index: 781450 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.2481. Min Act: -0.1700
Data Index: 1917014 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.2638. Min Act: -0.1700
Data Index: 7067247 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.2481. Min Act: -0.1700
Data Index: 1762598 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.2481. Min Act: -0.1700
Data Index: 1030616 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.2009. Min Act: -0.1700
Data Index: 3324947 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.2009. Min Act: -0.1700
Data Index: 5092094 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.1852. Min Act: -0.1700
Data Index: 7224901 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.1852. Min Act: -0.1700
Data Index: 707646 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.1852. Min Act: -0.1700
Data Index: 3225239 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.1695. Min Act: -0.1700
Data Index: 6523990 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4520. Min Range: -3.4520
Max Act: 3.1695. Min Act: -0.1700
Data Index: 2102337 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19