Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2161 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1974. Min Range: -5.1974
Max Act: 5.1974. Min Act: -0.1700
Data Index: 232461 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1974. Min Range: -5.1974
Max Act: 5.0724. Min Act: -0.1700
Data Index: 4974942 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1974. Min Range: -5.1974
Max Act: 5.0724. Min Act: -0.1700
Data Index: 7352285 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1974. Min Range: -5.1974
Max Act: 5.0412. Min Act: -0.1700
Data Index: 7047855 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1974. Min Range: -5.1974
Max Act: 5.0412. Min Act: -0.1700
Data Index: 1126060 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1974. Min Range: -5.1974
Max Act: 5.0099. Min Act: -0.1700
Data Index: 4610332 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1974. Min Range: -5.1974
Max Act: 5.0099. Min Act: -0.1700
Data Index: 462451 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1974. Min Range: -5.1974
Max Act: 5.0099. Min Act: -0.1700
Data Index: 3753456 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1974. Min Range: -5.1974
Max Act: 5.0099. Min Act: -0.1700
Data Index: 6403114 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1974. Min Range: -5.1974
Max Act: 5.0099. Min Act: -0.1700
Data Index: 7356345 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1974. Min Range: -5.1974
Max Act: 4.9787. Min Act: -0.1700
Data Index: 2636493 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1974. Min Range: -5.1974
Max Act: 4.9474. Min Act: -0.1700
Data Index: 6807709 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1974. Min Range: -5.1974
Max Act: 4.9162. Min Act: -0.1700
Data Index: 5365465 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1974. Min Range: -5.1974
Max Act: 4.9474. Min Act: -0.1700
Data Index: 1018842 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1974. Min Range: -5.1974
Max Act: 4.9474. Min Act: -0.1700
Data Index: 1683656 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1974. Min Range: -5.1974
Max Act: 4.9474. Min Act: -0.1700
Data Index: 325103 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1974. Min Range: -5.1974
Max Act: 4.9474. Min Act: -0.1700
Data Index: 1447793 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1974. Min Range: -5.1974
Max Act: 4.9474. Min Act: -0.1700
Data Index: 6804349 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1974. Min Range: -5.1974
Max Act: 4.9474. Min Act: -0.1700
Data Index: 1252463 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1974. Min Range: -5.1974
Max Act: 4.9474. Min Act: -0.1700
Data Index: 2299656 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19