Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5606 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.6413. Min Act: -0.1700
Data Index: 5634998 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.6100. Min Act: -0.1700
Data Index: 5341389 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.5943. Min Act: -0.1700
Data Index: 3190219 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.5787. Min Act: -0.1700
Data Index: 4168804 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.5787. Min Act: -0.1700
Data Index: 4383525 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.5630. Min Act: -0.1700
Data Index: 8125349 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.5317. Min Act: -0.1700
Data Index: 6948050 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.5160. Min Act: -0.1700
Data Index: 7584433 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.5004. Min Act: -0.1700
Data Index: 7809509 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4690. Min Act: -0.1700
Data Index: 4882195 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4690. Min Act: -0.1700
Data Index: 8003895 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4690. Min Act: -0.1700
Data Index: 372460 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4690. Min Act: -0.1700
Data Index: 1266625 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4690. Min Act: -0.1700
Data Index: 8241497 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4690. Min Act: -0.1700
Data Index: 3171244 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4534. Min Act: -0.1700
Data Index: 5219796 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4534. Min Act: -0.1700
Data Index: 8558951 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4534. Min Act: -0.1700
Data Index: 5226379 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4534. Min Act: -0.1700
Data Index: 815011 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6413. Min Range: -3.6413
Max Act: 3.4377. Min Act: -0.1700
Data Index: 5900978 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19