Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3324 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2299. Min Range: -8.2299
Max Act: 8.2299. Min Act: -0.1700
Data Index: 5350 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2299. Min Range: -8.2299
Max Act: 8.1362. Min Act: -0.1700
Data Index: 3009467 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2299. Min Range: -8.2299
Max Act: 8.1674. Min Act: -0.1700
Data Index: 7728939 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2299. Min Range: -8.2299
Max Act: 8.1362. Min Act: -0.1700
Data Index: 7195772 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2299. Min Range: -8.2299
Max Act: 8.0424. Min Act: -0.1700
Data Index: 4560596 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2299. Min Range: -8.2299
Max Act: 8.0112. Min Act: -0.1700
Data Index: 3333249 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.9487. Min Act: -0.1700
Data Index: 7043078 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.9799. Min Act: -0.1700
Data Index: 3257521 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.9174. Min Act: -0.1700
Data Index: 8395446 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.8549. Min Act: -0.1700
Data Index: 1512133 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.7924. Min Act: -0.1700
Data Index: 2743641 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.7924. Min Act: -0.1700
Data Index: 2649838 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.7924. Min Act: -0.1700
Data Index: 6821470 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.7612. Min Act: -0.1700
Data Index: 1888307 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.7612. Min Act: -0.1700
Data Index: 6376324 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.6674. Min Act: -0.1700
Data Index: 2953799 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.6674. Min Act: -0.1700
Data Index: 8185816 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.6674. Min Act: -0.1700
Data Index: 6625485 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.6674. Min Act: -0.1700
Data Index: 4027560 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2299. Min Range: -8.2299
Max Act: 7.6362. Min Act: -0.1700
Data Index: 3355234 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19