Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2378 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.8891. Min Act: -0.1700
Data Index: 1126624 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.8578. Min Act: -0.1700
Data Index: 1974628 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.8578. Min Act: -0.1700
Data Index: 2511958 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.8266. Min Act: -0.1700
Data Index: 903732 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.8266. Min Act: -0.1700
Data Index: 2852402 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.7953. Min Act: -0.1700
Data Index: 7290653 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.7641. Min Act: -0.1700
Data Index: 4608000 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.7641. Min Act: -0.1700
Data Index: 2255946 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.7328. Min Act: -0.1700
Data Index: 5805458 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.7328. Min Act: -0.1700
Data Index: 7071237 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.7016. Min Act: -0.1700
Data Index: 537493 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.7328. Min Act: -0.1700
Data Index: 5345400 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.7016. Min Act: -0.1700
Data Index: 4327632 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.7328. Min Act: -0.1700
Data Index: 3235058 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.6703. Min Act: -0.1700
Data Index: 5283657 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.6703. Min Act: -0.1700
Data Index: 5083277 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.6703. Min Act: -0.1700
Data Index: 1864714 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.7016. Min Act: -0.1700
Data Index: 903731 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.6703. Min Act: -0.1700
Data Index: 3028215 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8891. Min Range: -4.8891
Max Act: 4.6703. Min Act: -0.1700
Data Index: 5676965 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19