Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 99 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.1480. Min Act: -0.1700
Data Index: 1122284 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.1007. Min Act: -0.1700
Data Index: 1586045 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.1007. Min Act: -0.1700
Data Index: 613002 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0849. Min Act: -0.1700
Data Index: 982512 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0692. Min Act: -0.1700
Data Index: 3133482 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0692. Min Act: -0.1700
Data Index: 2339870 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0692. Min Act: -0.1700
Data Index: 2375190 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0692. Min Act: -0.1700
Data Index: 2282000 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0692. Min Act: -0.1700
Data Index: 3035167 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0534. Min Act: -0.1700
Data Index: 1111159 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0376. Min Act: -0.1700
Data Index: 1750141 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0376. Min Act: -0.1700
Data Index: 6198879 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0218. Min Act: -0.1700
Data Index: 2843893 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0376. Min Act: -0.1700
Data Index: 3144937 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0218. Min Act: -0.1700
Data Index: 4889372 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0218. Min Act: -0.1700
Data Index: 429255 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0218. Min Act: -0.1700
Data Index: 6484056 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0218. Min Act: -0.1700
Data Index: 4290689 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0218. Min Act: -0.1700
Data Index: 3870045 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1480. Min Range: -3.1480
Max Act: 3.0060. Min Act: -0.1700
Data Index: 4179749 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19