Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.8331. Min Act: -0.1700
Data Index: 81379 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.8331. Min Act: -0.1700
Data Index: 8169654 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.7393. Min Act: -0.1700
Data Index: 3909643 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.7393. Min Act: -0.1700
Data Index: 6884414 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.6143. Min Act: -0.1700
Data Index: 5474048 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.5831. Min Act: -0.1700
Data Index: 1185798 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.5831. Min Act: -0.1700
Data Index: 3212214 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.5518. Min Act: -0.1700
Data Index: 7303923 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.5518. Min Act: -0.1700
Data Index: 1236219 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.5206. Min Act: -0.1700
Data Index: 3560477 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.4268. Min Act: -0.1700
Data Index: 3466340 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.4581. Min Act: -0.1700
Data Index: 2598670 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.4268. Min Act: -0.1700
Data Index: 3463822 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.3643. Min Act: -0.1700
Data Index: 6599875 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.3956. Min Act: -0.1700
Data Index: 885234 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.3956. Min Act: -0.1700
Data Index: 3646177 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.3643. Min Act: -0.1700
Data Index: 8230169 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.3643. Min Act: -0.1700
Data Index: 3377220 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.3331. Min Act: -0.1700
Data Index: 1495988 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8331. Min Range: -5.8331
Max Act: 5.3331. Min Act: -0.1700
Data Index: 4214286 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19