Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1697 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.7252. Min Act: -0.1700
Data Index: 8476608 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.6314. Min Act: -0.1700
Data Index: 1192721 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.5689. Min Act: -0.1700
Data Index: 2862301 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.3814. Min Act: -0.1700
Data Index: 4052728 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.3814. Min Act: -0.1700
Data Index: 6367313 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.3814. Min Act: -0.1700
Data Index: 1161880 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.3502. Min Act: -0.1700
Data Index: 3325708 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.3502. Min Act: -0.1700
Data Index: 3583 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.2876. Min Act: -0.1700
Data Index: 2715257 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.3189. Min Act: -0.1700
Data Index: 6344367 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.2876. Min Act: -0.1700
Data Index: 4389557 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.2564. Min Act: -0.1700
Data Index: 5889132 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.2564. Min Act: -0.1700
Data Index: 5751594 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.2564. Min Act: -0.1700
Data Index: 5973464 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.2564. Min Act: -0.1700
Data Index: 1292448 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.2564. Min Act: -0.1700
Data Index: 7978783 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.2564. Min Act: -0.1700
Data Index: 7709610 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.2251. Min Act: -0.1700
Data Index: 1404927 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.2251. Min Act: -0.1700
Data Index: 2581418 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7252. Min Range: -4.7252
Max Act: 4.1939. Min Act: -0.1700
Data Index: 6536210 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19