Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1218 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0790. Min Range: -8.0790
Max Act: 8.0790. Min Act: -0.1700
Data Index: 205186 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.6415. Min Act: -0.1700
Data Index: 1536077 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.4540. Min Act: -0.1700
Data Index: 8707212 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.3290. Min Act: -0.1700
Data Index: 4545653 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.3290. Min Act: -0.1700
Data Index: 1944645 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.2353. Min Act: -0.1700
Data Index: 4453829 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.1728. Min Act: -0.1700
Data Index: 912502 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.1728. Min Act: -0.1700
Data Index: 7214394 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.1103. Min Act: -0.1700
Data Index: 7618816 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.1103. Min Act: -0.1700
Data Index: 8287678 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.0478. Min Act: -0.1700
Data Index: 458603 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.0165. Min Act: -0.1700
Data Index: 6963644 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0790. Min Range: -8.0790
Max Act: 7.0165. Min Act: -0.1700
Data Index: 3579628 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0790. Min Range: -8.0790
Max Act: 6.9228. Min Act: -0.1700
Data Index: 123684 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0790. Min Range: -8.0790
Max Act: 6.8290. Min Act: -0.1700
Data Index: 7633346 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0790. Min Range: -8.0790
Max Act: 6.8290. Min Act: -0.1700
Data Index: 1185587 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0790. Min Range: -8.0790
Max Act: 6.8290. Min Act: -0.1700
Data Index: 4377592 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0790. Min Range: -8.0790
Max Act: 6.7978. Min Act: -0.1700
Data Index: 686058 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0790. Min Range: -8.0790
Max Act: 6.7978. Min Act: -0.1700
Data Index: 7813860 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0790. Min Range: -8.0790
Max Act: 6.8290. Min Act: -0.1700
Data Index: 8071266 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19