Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3433. Min Range: -4.3433
Max Act: 4.3433. Min Act: -0.1700
Data Index: 6757755 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3433. Min Range: -4.3433
Max Act: 4.1245. Min Act: -0.1700
Data Index: 930427 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3433. Min Range: -4.3433
Max Act: 4.0307. Min Act: -0.1700
Data Index: 8822483 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3433. Min Range: -4.3433
Max Act: 4.0307. Min Act: -0.1700
Data Index: 3088542 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3433. Min Range: -4.3433
Max Act: 4.0307. Min Act: -0.1700
Data Index: 6352534 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9995. Min Act: -0.1700
Data Index: 8461564 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9682. Min Act: -0.1700
Data Index: 425194 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9682. Min Act: -0.1700
Data Index: 7092212 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9995. Min Act: -0.1700
Data Index: 1975910 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9682. Min Act: -0.1700
Data Index: 6370435 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9682. Min Act: -0.1700
Data Index: 1770075 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9369. Min Act: -0.1700
Data Index: 3565569 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9682. Min Act: -0.1700
Data Index: 7931930 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9682. Min Act: -0.1700
Data Index: 7209413 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9682. Min Act: -0.1700
Data Index: 5769895 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9682. Min Act: -0.1700
Data Index: 5117526 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9369. Min Act: -0.1700
Data Index: 6536802 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9057. Min Act: -0.1700
Data Index: 6878084 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9369. Min Act: -0.1700
Data Index: 3817885 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3433. Min Range: -4.3433
Max Act: 3.9682. Min Act: -0.1700
Data Index: 2076263 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19