Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3169 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.7485. Min Act: -0.1700
Data Index: 1931398 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.5610. Min Act: -0.1700
Data Index: 6928539 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.4360. Min Act: -0.1700
Data Index: 3115004 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.3423. Min Act: -0.1700
Data Index: 8320160 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.3110. Min Act: -0.1700
Data Index: 3467278 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.3110. Min Act: -0.1700
Data Index: 3725685 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2798. Min Act: -0.1700
Data Index: 7699439 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2798. Min Act: -0.1700
Data Index: 8724684 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2798. Min Act: -0.1700
Data Index: 4752490 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2485. Min Act: -0.1700
Data Index: 1168745 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.2173. Min Act: -0.1700
Data Index: 5767739 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.1860. Min Act: -0.1700
Data Index: 4323319 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.1548. Min Act: -0.1700
Data Index: 7583487 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.1548. Min Act: -0.1700
Data Index: 3975490 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.1548. Min Act: -0.1700
Data Index: 2075469 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.1235. Min Act: -0.1700
Data Index: 5372506 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.1235. Min Act: -0.1700
Data Index: 2483265 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.1235. Min Act: -0.1700
Data Index: 7970343 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.1235. Min Act: -0.1700
Data Index: 4645390 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7485. Min Range: -5.7485
Max Act: 5.0923. Min Act: -0.1700
Data Index: 5100472 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19