Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.6251. Min Act: -0.1700
Data Index: 2295911 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.5930. Min Act: -0.1700
Data Index: 1151800 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.5768. Min Act: -0.1700
Data Index: 1161610 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.5607. Min Act: -0.1700
Data Index: 2405683 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.5284. Min Act: -0.1700
Data Index: 7601847 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.5122. Min Act: -0.1700
Data Index: 7656621 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.5122. Min Act: -0.1700
Data Index: 703866 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4960. Min Act: -0.1700
Data Index: 5502382 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4960. Min Act: -0.1700
Data Index: 6469470 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4798. Min Act: -0.1700
Data Index: 5510411 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4798. Min Act: -0.1700
Data Index: 7745109 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4636. Min Act: -0.1700
Data Index: 5574330 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4636. Min Act: -0.1700
Data Index: 5162757 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4636. Min Act: -0.1700
Data Index: 5527648 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4636. Min Act: -0.1700
Data Index: 7396627 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4473. Min Act: -0.1700
Data Index: 2484371 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4636. Min Act: -0.1700
Data Index: 4846823 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4311. Min Act: -0.1700
Data Index: 6342407 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4473. Min Act: -0.1700
Data Index: 6779141 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6251. Min Range: -2.6251
Max Act: 2.4473. Min Act: -0.1700
Data Index: 5703399 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19