Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4833 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.5103. Min Act: -0.1700
Data Index: 7213244 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.5103. Min Act: -0.1700
Data Index: 7213243 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.4790. Min Act: -0.1700
Data Index: 8664544 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.4165. Min Act: -0.1700
Data Index: 1285309 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.3853. Min Act: -0.1700
Data Index: 7213245 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.3853. Min Act: -0.1700
Data Index: 7273972 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.3540. Min Act: -0.1700
Data Index: 6921075 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.3228. Min Act: -0.1700
Data Index: 247818 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.3228. Min Act: -0.1700
Data Index: 8240301 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.3228. Min Act: -0.1700
Data Index: 4094289 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.2915. Min Act: -0.1700
Data Index: 6064551 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.2915. Min Act: -0.1700
Data Index: 8315821 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.2603. Min Act: -0.1700
Data Index: 7680004 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.2915. Min Act: -0.1700
Data Index: 2891077 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.2603. Min Act: -0.1700
Data Index: 5018670 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.2290. Min Act: -0.1700
Data Index: 5322514 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.2290. Min Act: -0.1700
Data Index: 4959375 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.2290. Min Act: -0.1700
Data Index: 5420921 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.2290. Min Act: -0.1700
Data Index: 3881112 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5103. Min Range: -5.5103
Max Act: 5.1978. Min Act: -0.1700
Data Index: 6064529 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19