Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 552 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.4125. Min Act: -0.1700
Data Index: 6822757 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.4125. Min Act: -0.1700
Data Index: 2527373 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.3498. Min Act: -0.1700
Data Index: 1430658 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.3341. Min Act: -0.1700
Data Index: 2295890 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.3498. Min Act: -0.1700
Data Index: 1517560 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.3184. Min Act: -0.1700
Data Index: 6192599 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.3027. Min Act: -0.1700
Data Index: 3010862 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2870. Min Act: -0.1700
Data Index: 2823437 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2870. Min Act: -0.1700
Data Index: 7809374 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2713. Min Act: -0.1700
Data Index: 6670635 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2556. Min Act: -0.1700
Data Index: 4852477 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2399. Min Act: -0.1700
Data Index: 5493581 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2399. Min Act: -0.1700
Data Index: 8078593 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2399. Min Act: -0.1700
Data Index: 1780278 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2399. Min Act: -0.1700
Data Index: 8517458 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2399. Min Act: -0.1700
Data Index: 4674524 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2241. Min Act: -0.1700
Data Index: 2607768 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2241. Min Act: -0.1700
Data Index: 386463 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2241. Min Act: -0.1700
Data Index: 4483210 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4125. Min Range: -3.4125
Max Act: 3.2084. Min Act: -0.1700
Data Index: 708103 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19