Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1451 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0314. Min Range: -8.0314
Max Act: 8.0314. Min Act: -0.1700
Data Index: 2520261 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.9689. Min Act: -0.1700
Data Index: 7612422 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.9689. Min Act: -0.1700
Data Index: 2173935 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.8439. Min Act: -0.1700
Data Index: 420945 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.7814. Min Act: -0.1700
Data Index: 8560906 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.7814. Min Act: -0.1700
Data Index: 5832211 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.7814. Min Act: -0.1700
Data Index: 3138768 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.7189. Min Act: -0.1700
Data Index: 3395671 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.7189. Min Act: -0.1700
Data Index: 2054799 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.7189. Min Act: -0.1700
Data Index: 7510953 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.7189. Min Act: -0.1700
Data Index: 8065127 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.6564. Min Act: -0.1700
Data Index: 1464191 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.7189. Min Act: -0.1700
Data Index: 2949291 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.7189. Min Act: -0.1700
Data Index: 5438400 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.6564. Min Act: -0.1700
Data Index: 1295925 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.6564. Min Act: -0.1700
Data Index: 4038427 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.6564. Min Act: -0.1700
Data Index: 2468534 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.6564. Min Act: -0.1700
Data Index: 6463211 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.6564. Min Act: -0.1700
Data Index: 6968783 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0314. Min Range: -8.0314
Max Act: 7.6251. Min Act: -0.1700
Data Index: 6718892 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19