Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1897 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.3865. Min Range: -10.3865
Max Act: 10.3865. Min Act: -0.1700
Data Index: 199949 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3865. Min Range: -10.3865
Max Act: 10.2615. Min Act: -0.1700
Data Index: 161197 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3865. Min Range: -10.3865
Max Act: 10.2615. Min Act: -0.1700
Data Index: 6811204 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3865. Min Range: -10.3865
Max Act: 10.0740. Min Act: -0.1700
Data Index: 5554522 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3865. Min Range: -10.3865
Max Act: 10.0740. Min Act: -0.1700
Data Index: 1309533 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.9490. Min Act: -0.1700
Data Index: 4387074 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3865. Min Range: -10.3865
Max Act: 10.0115. Min Act: -0.1700
Data Index: 7505397 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.8865. Min Act: -0.1700
Data Index: 3223583 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.9490. Min Act: -0.1700
Data Index: 5896951 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.8865. Min Act: -0.1700
Data Index: 5028604 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.9490. Min Act: -0.1700
Data Index: 7768443 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.8240. Min Act: -0.1700
Data Index: 2244001 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.8865. Min Act: -0.1700
Data Index: 1049548 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.7615. Min Act: -0.1700
Data Index: 656353 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.8240. Min Act: -0.1700
Data Index: 3599478 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.6990. Min Act: -0.1700
Data Index: 5866561 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.6990. Min Act: -0.1700
Data Index: 1635422 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.6365. Min Act: -0.1700
Data Index: 66158 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.6365. Min Act: -0.1700
Data Index: 1422210 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3865. Min Range: -10.3865
Max Act: 9.6990. Min Act: -0.1700
Data Index: 2714105 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19