Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1620 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.5606. Min Act: -0.1700
Data Index: 3083294 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.3731. Min Act: -0.1700
Data Index: 8009068 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.3418. Min Act: -0.1700
Data Index: 8603539 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.2793. Min Act: -0.1700
Data Index: 2286005 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.2481. Min Act: -0.1700
Data Index: 6462182 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.1856. Min Act: -0.1700
Data Index: 1755628 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.1856. Min Act: -0.1700
Data Index: 6871328 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.1543. Min Act: -0.1700
Data Index: 181585 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.0918. Min Act: -0.1700
Data Index: 8525959 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.1543. Min Act: -0.1700
Data Index: 5191467 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.0606. Min Act: -0.1700
Data Index: 7824628 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.1231. Min Act: -0.1700
Data Index: 7913090 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.0918. Min Act: -0.1700
Data Index: 2952267 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.0918. Min Act: -0.1700
Data Index: 7558588 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.0918. Min Act: -0.1700
Data Index: 3615935 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.0918. Min Act: -0.1700
Data Index: 5521348 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.0918. Min Act: -0.1700
Data Index: 5345630 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.0918. Min Act: -0.1700
Data Index: 1532664 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.0918. Min Act: -0.1700
Data Index: 5101897 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5606. Min Range: -5.5606
Max Act: 5.0606. Min Act: -0.1700
Data Index: 5578993 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19