Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 946 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.5586. Min Act: -0.1700
Data Index: 1358290 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.4023. Min Act: -0.1700
Data Index: 4922179 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.3086. Min Act: -0.1700
Data Index: 6783709 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.1836. Min Act: -0.1700
Data Index: 7737327 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.1523. Min Act: -0.1700
Data Index: 7098517 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.1211. Min Act: -0.1700
Data Index: 3270056 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.0898. Min Act: -0.1700
Data Index: 4206191 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.0898. Min Act: -0.1700
Data Index: 7060787 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.0586. Min Act: -0.1700
Data Index: 105589 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.0586. Min Act: -0.1700
Data Index: 1619014 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.0898. Min Act: -0.1700
Data Index: 6801207 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.0273. Min Act: -0.1700
Data Index: 3875840 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5586. Min Range: -6.5586
Max Act: 6.0273. Min Act: -0.1700
Data Index: 4421635 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5586. Min Range: -6.5586
Max Act: 5.9961. Min Act: -0.1700
Data Index: 5889344 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5586. Min Range: -6.5586
Max Act: 5.9961. Min Act: -0.1700
Data Index: 2923920 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5586. Min Range: -6.5586
Max Act: 5.9961. Min Act: -0.1700
Data Index: 6829210 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5586. Min Range: -6.5586
Max Act: 5.9648. Min Act: -0.1700
Data Index: 731023 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5586. Min Range: -6.5586
Max Act: 5.9648. Min Act: -0.1700
Data Index: 5825322 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5586. Min Range: -6.5586
Max Act: 5.9336. Min Act: -0.1700
Data Index: 3501048 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5586. Min Range: -6.5586
Max Act: 5.9648. Min Act: -0.1700
Data Index: 2689082 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19