Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.4579. Min Act: -0.1700
Data Index: 6654612 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.3952. Min Act: -0.1700
Data Index: 6998265 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.4265. Min Act: -0.1700
Data Index: 3475588 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.3795. Min Act: -0.1700
Data Index: 4155525 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.3638. Min Act: -0.1700
Data Index: 2807778 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.3638. Min Act: -0.1700
Data Index: 3475589 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.3481. Min Act: -0.1700
Data Index: 1695293 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.3011. Min Act: -0.1700
Data Index: 54227 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2854. Min Act: -0.1700
Data Index: 6877887 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2854. Min Act: -0.1700
Data Index: 6877888 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2854. Min Act: -0.1700
Data Index: 1140286 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.3011. Min Act: -0.1700
Data Index: 134938 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2539. Min Act: -0.1700
Data Index: 7608722 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2696. Min Act: -0.1700
Data Index: 2222781 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2539. Min Act: -0.1700
Data Index: 65723 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2382. Min Act: -0.1700
Data Index: 6031400 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2382. Min Act: -0.1700
Data Index: 1559865 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2382. Min Act: -0.1700
Data Index: 3257561 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2225. Min Act: -0.1700
Data Index: 1762921 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4579. Min Range: -3.4579
Max Act: 3.2225. Min Act: -0.1700
Data Index: 2804860 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19