Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2471 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.1352. Min Act: -0.1700
Data Index: 7222538 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.1039. Min Act: -0.1700
Data Index: 15099 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.9789. Min Act: -0.1700
Data Index: 4466253 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.9789. Min Act: -0.1700
Data Index: 3454612 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.9789. Min Act: -0.1700
Data Index: 1357994 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 609929 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8539. Min Act: -0.1700
Data Index: 3051667 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 7225623 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7914. Min Act: -0.1700
Data Index: 2346219 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7914. Min Act: -0.1700
Data Index: 2373951 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7602. Min Act: -0.1700
Data Index: 2471697 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7602. Min Act: -0.1700
Data Index: 139232 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 480782 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7289. Min Act: -0.1700
Data Index: 8121703 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 8103821 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 989048 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 8130408 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6664. Min Act: -0.1700
Data Index: 5262622 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 1283195 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6664. Min Act: -0.1700
Data Index: 7705248 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19