Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3718 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5689. Min Range: -7.5689
Max Act: 7.5689. Min Act: -0.1700
Data Index: 7289066 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5689. Min Range: -7.5689
Max Act: 7.2252. Min Act: -0.1700
Data Index: 1376756 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5689. Min Range: -7.5689
Max Act: 7.1939. Min Act: -0.1700
Data Index: 599411 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5689. Min Range: -7.5689
Max Act: 7.0689. Min Act: -0.1700
Data Index: 3469282 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5689. Min Range: -7.5689
Max Act: 7.0064. Min Act: -0.1700
Data Index: 4742198 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.9752. Min Act: -0.1700
Data Index: 3976273 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.9439. Min Act: -0.1700
Data Index: 567593 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.8502. Min Act: -0.1700
Data Index: 7749873 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.7877. Min Act: -0.1700
Data Index: 8550415 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.7564. Min Act: -0.1700
Data Index: 7797219 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.7564. Min Act: -0.1700
Data Index: 3292998 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.7252. Min Act: -0.1700
Data Index: 1755574 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.6627. Min Act: -0.1700
Data Index: 1383774 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.6002. Min Act: -0.1700
Data Index: 284044 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.6314. Min Act: -0.1700
Data Index: 4883431 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.6627. Min Act: -0.1700
Data Index: 7220960 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.5689. Min Act: -0.1700
Data Index: 5336662 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.6314. Min Act: -0.1700
Data Index: 36238 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.6002. Min Act: -0.1700
Data Index: 4048796 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5689. Min Range: -7.5689
Max Act: 6.5377. Min Act: -0.1700
Data Index: 5943645 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19