Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3314 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0888. Min Range: -9.0888
Max Act: 9.0888. Min Act: -0.1700
Data Index: 1006601 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.7763. Min Act: -0.1700
Data Index: 1817400 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.7138. Min Act: -0.1700
Data Index: 5414778 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.7138. Min Act: -0.1700
Data Index: 7883780 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.5263. Min Act: -0.1700
Data Index: 9994 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.4638. Min Act: -0.1700
Data Index: 3159224 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.4638. Min Act: -0.1700
Data Index: 3720521 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.4013. Min Act: -0.1700
Data Index: 1749634 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.4013. Min Act: -0.1700
Data Index: 7818982 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.4013. Min Act: -0.1700
Data Index: 8231590 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.3388. Min Act: -0.1700
Data Index: 6360109 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.4013. Min Act: -0.1700
Data Index: 5968042 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.3388. Min Act: -0.1700
Data Index: 7703953 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.3388. Min Act: -0.1700
Data Index: 6102274 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.2763. Min Act: -0.1700
Data Index: 8793322 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.2763. Min Act: -0.1700
Data Index: 3886392 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.2763. Min Act: -0.1700
Data Index: 2297266 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.2138. Min Act: -0.1700
Data Index: 1559492 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.2138. Min Act: -0.1700
Data Index: 3863309 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0888. Min Range: -9.0888
Max Act: 8.2138. Min Act: -0.1700
Data Index: 4067656 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19