Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6384 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2410. Min Range: -7.2410
Max Act: 7.2410. Min Act: -0.1700
Data Index: 6865476 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2410. Min Range: -7.2410
Max Act: 7.1785. Min Act: -0.1700
Data Index: 8418316 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2410. Min Range: -7.2410
Max Act: 7.0222. Min Act: -0.1700
Data Index: 1569132 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.9597. Min Act: -0.1700
Data Index: 6265404 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.8972. Min Act: -0.1700
Data Index: 7517335 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.9285. Min Act: -0.1700
Data Index: 1498453 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.9285. Min Act: -0.1700
Data Index: 3716178 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.8347. Min Act: -0.1700
Data Index: 6233595 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.8660. Min Act: -0.1700
Data Index: 4047114 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.8347. Min Act: -0.1700
Data Index: 992035 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.8035. Min Act: -0.1700
Data Index: 2676342 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.8035. Min Act: -0.1700
Data Index: 5910303 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.8035. Min Act: -0.1700
Data Index: 3382491 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.8035. Min Act: -0.1700
Data Index: 5497594 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.7722. Min Act: -0.1700
Data Index: 1853007 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.7722. Min Act: -0.1700
Data Index: 4460161 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.7722. Min Act: -0.1700
Data Index: 6893301 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.7410. Min Act: -0.1700
Data Index: 3462267 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.7410. Min Act: -0.1700
Data Index: 4423733 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2410. Min Range: -7.2410
Max Act: 6.7097. Min Act: -0.1700
Data Index: 426984 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19