Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1340 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5417. Min Range: -6.5417
Max Act: 6.5417. Min Act: -0.1700
Data Index: 913002 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5417. Min Range: -6.5417
Max Act: 6.2605. Min Act: -0.1700
Data Index: 4958849 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5417. Min Range: -6.5417
Max Act: 6.2605. Min Act: -0.1700
Data Index: 6438165 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5417. Min Range: -6.5417
Max Act: 6.2292. Min Act: -0.1700
Data Index: 428081 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.9480. Min Act: -0.1700
Data Index: 7927163 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.8855. Min Act: -0.1700
Data Index: 8441655 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.9480. Min Act: -0.1700
Data Index: 2742668 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.9167. Min Act: -0.1700
Data Index: 2110339 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.8855. Min Act: -0.1700
Data Index: 5138440 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.8542. Min Act: -0.1700
Data Index: 1613696 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.8230. Min Act: -0.1700
Data Index: 3266219 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.8230. Min Act: -0.1700
Data Index: 6267621 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.8230. Min Act: -0.1700
Data Index: 4355750 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.7917. Min Act: -0.1700
Data Index: 2075809 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.7605. Min Act: -0.1700
Data Index: 3310152 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.7605. Min Act: -0.1700
Data Index: 8015128 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.7292. Min Act: -0.1700
Data Index: 4609979 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.7292. Min Act: -0.1700
Data Index: 3373523 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.7605. Min Act: -0.1700
Data Index: 7942047 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5417. Min Range: -6.5417
Max Act: 5.7292. Min Act: -0.1700
Data Index: 5027639 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19