Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 552 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2351. Min Range: -4.2351
Max Act: 4.2351. Min Act: -0.1700
Data Index: 6794481 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2351. Min Range: -4.2351
Max Act: 4.0163. Min Act: -0.1700
Data Index: 3907134 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.9225. Min Act: -0.1700
Data Index: 8495231 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.8913. Min Act: -0.1700
Data Index: 1164252 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.8600. Min Act: -0.1700
Data Index: 1164257 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.8600. Min Act: -0.1700
Data Index: 854489 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.8287. Min Act: -0.1700
Data Index: 4320989 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.8287. Min Act: -0.1700
Data Index: 6910266 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.8287. Min Act: -0.1700
Data Index: 4988369 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.8600. Min Act: -0.1700
Data Index: 1312841 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.8287. Min Act: -0.1700
Data Index: 4414769 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.8287. Min Act: -0.1700
Data Index: 4497493 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.7975. Min Act: -0.1700
Data Index: 3386613 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.7975. Min Act: -0.1700
Data Index: 469837 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.7975. Min Act: -0.1700
Data Index: 1012460 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.7975. Min Act: -0.1700
Data Index: 2318502 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.7975. Min Act: -0.1700
Data Index: 4666167 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.7662. Min Act: -0.1700
Data Index: 8700074 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.7662. Min Act: -0.1700
Data Index: 7101627 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2351. Min Range: -4.2351
Max Act: 3.7975. Min Act: -0.1700
Data Index: 3144382 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19