Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1875 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.8004. Min Act: -0.1700
Data Index: 6591617 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.6129. Min Act: -0.1700
Data Index: 7419985 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.6129. Min Act: -0.1700
Data Index: 3268636 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.6129. Min Act: -0.1700
Data Index: 6554545 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.6129. Min Act: -0.1700
Data Index: 1046068 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.6129. Min Act: -0.1700
Data Index: 7489075 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5817. Min Act: -0.1700
Data Index: 1174175 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5817. Min Act: -0.1700
Data Index: 718296 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5817. Min Act: -0.1700
Data Index: 4827634 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5817. Min Act: -0.1700
Data Index: 2892946 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5504. Min Act: -0.1700
Data Index: 6093643 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5504. Min Act: -0.1700
Data Index: 8681607 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5504. Min Act: -0.1700
Data Index: 1096453 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5504. Min Act: -0.1700
Data Index: 5423492 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5192. Min Act: -0.1700
Data Index: 5090804 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5504. Min Act: -0.1700
Data Index: 1556239 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5504. Min Act: -0.1700
Data Index: 371073 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5192. Min Act: -0.1700
Data Index: 1533400 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5504. Min Act: -0.1700
Data Index: 4686580 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8004. Min Range: -5.8004
Max Act: 5.5504. Min Act: -0.1700
Data Index: 536212 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19