Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1818 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.7299. Min Act: -0.1700
Data Index: 5581903 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.6986. Min Act: -0.1700
Data Index: 2030504 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.6830. Min Act: -0.1700
Data Index: 4796182 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.6673. Min Act: -0.1700
Data Index: 5577627 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.6204. Min Act: -0.1700
Data Index: 5163912 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.6204. Min Act: -0.1700
Data Index: 2202011 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5734. Min Act: -0.1700
Data Index: 8775208 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5734. Min Act: -0.1700
Data Index: 3537199 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5734. Min Act: -0.1700
Data Index: 4220415 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5734. Min Act: -0.1700
Data Index: 3597537 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5421. Min Act: -0.1700
Data Index: 553211 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5421. Min Act: -0.1700
Data Index: 414324 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5421. Min Act: -0.1700
Data Index: 4266380 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5264. Min Act: -0.1700
Data Index: 5954837 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5108. Min Act: -0.1700
Data Index: 5961463 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.4951. Min Act: -0.1700
Data Index: 8317118 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5108. Min Act: -0.1700
Data Index: 2021851 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.4951. Min Act: -0.1700
Data Index: 162851 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.5108. Min Act: -0.1700
Data Index: 5733186 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7299. Min Range: -3.7299
Max Act: 3.4951. Min Act: -0.1700
Data Index: 176248 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19