Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2690 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2396. Min Range: -6.2396
Max Act: 6.2396. Min Act: -0.1700
Data Index: 1697611 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2396. Min Range: -6.2396
Max Act: 6.1771. Min Act: -0.1700
Data Index: 5914921 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.8646. Min Act: -0.1700
Data Index: 5600434 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.8646. Min Act: -0.1700
Data Index: 7377221 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.8958. Min Act: -0.1700
Data Index: 8058683 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.8958. Min Act: -0.1700
Data Index: 3967232 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.8333. Min Act: -0.1700
Data Index: 2102637 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.8333. Min Act: -0.1700
Data Index: 6880330 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.8021. Min Act: -0.1700
Data Index: 1125456 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.7708. Min Act: -0.1700
Data Index: 5785018 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.6771. Min Act: -0.1700
Data Index: 464970 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.7083. Min Act: -0.1700
Data Index: 5509789 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.7396. Min Act: -0.1700
Data Index: 363375 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.6771. Min Act: -0.1700
Data Index: 4403259 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.7083. Min Act: -0.1700
Data Index: 4855013 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.6771. Min Act: -0.1700
Data Index: 2222833 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.6146. Min Act: -0.1700
Data Index: 4533984 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.6458. Min Act: -0.1700
Data Index: 3986823 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.6771. Min Act: -0.1700
Data Index: 2559961 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2396. Min Range: -6.2396
Max Act: 5.6771. Min Act: -0.1700
Data Index: 7367760 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19