Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.3158. Min Act: -0.1700
Data Index: 3975979 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1924. Min Act: -0.1700
Data Index: 2904760 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1748. Min Act: -0.1700
Data Index: 4363706 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1572. Min Act: -0.1700
Data Index: 4115181 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1572. Min Act: -0.1700
Data Index: 5632904 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1572. Min Act: -0.1700
Data Index: 285828 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1221. Min Act: -0.1700
Data Index: 429928 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1396. Min Act: -0.1694
Data Index: 2478525 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1045. Min Act: -0.1698
Data Index: 483291 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1221. Min Act: -0.1700
Data Index: 5228120 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1221. Min Act: -0.1700
Data Index: 6872971 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1045. Min Act: -0.1699
Data Index: 5560159 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.1045. Min Act: -0.1694
Data Index: 4502556 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.0870. Min Act: -0.1700
Data Index: 6942428 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.0695. Min Act: -0.1694
Data Index: 4598629 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.0695. Min Act: -0.1699
Data Index: 8065718 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.0521. Min Act: -0.1700
Data Index: 528292 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.0521. Min Act: -0.1700
Data Index: 3597945 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.0521. Min Act: -0.1697
Data Index: 405780 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3158. Min Range: -1.3158
Max Act: 1.0521. Min Act: -0.1696
Data Index: 2911140 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19