Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2503. Min Range: -3.2503
Max Act: 3.2503. Min Act: -0.1700
Data Index: 753284 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2503. Min Range: -3.2503
Max Act: 3.1402. Min Act: -0.1700
Data Index: 2288458 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2503. Min Range: -3.2503
Max Act: 3.1244. Min Act: -0.1700
Data Index: 2361274 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2503. Min Range: -3.2503
Max Act: 3.0772. Min Act: -0.1700
Data Index: 4247736 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2503. Min Range: -3.2503
Max Act: 3.0614. Min Act: -0.1700
Data Index: 4334388 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.9824. Min Act: -0.1700
Data Index: 6465417 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.9508. Min Act: -0.1700
Data Index: 3999832 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.9508. Min Act: -0.1700
Data Index: 6502568 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.9508. Min Act: -0.1700
Data Index: 2204622 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.9508. Min Act: -0.1700
Data Index: 6892152 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.9191. Min Act: -0.1700
Data Index: 4836514 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.9191. Min Act: -0.1700
Data Index: 7627019 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.9349. Min Act: -0.1700
Data Index: 8183598 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.8874. Min Act: -0.1700
Data Index: 8027128 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.8715. Min Act: -0.1700
Data Index: 5379704 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.8556. Min Act: -0.1700
Data Index: 6027310 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.8715. Min Act: -0.1700
Data Index: 8081579 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.8715. Min Act: -0.1700
Data Index: 2032496 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.8715. Min Act: -0.1700
Data Index: 5160108 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2503. Min Range: -3.2503
Max Act: 2.8715. Min Act: -0.1700
Data Index: 367940 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19