Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6397 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.4998. Min Act: -0.1700
Data Index: 6115807 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.4998. Min Act: -0.1700
Data Index: 8153929 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.4373. Min Act: -0.1700
Data Index: 3119224 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.3748. Min Act: -0.1700
Data Index: 4830757 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.3748. Min Act: -0.1700
Data Index: 8333138 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.3748. Min Act: -0.1700
Data Index: 6024503 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.3748. Min Act: -0.1700
Data Index: 3005830 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.2498. Min Act: -0.1700
Data Index: 502336 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.2498. Min Act: -0.1700
Data Index: 3343118 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.2498. Min Act: -0.1700
Data Index: 3395838 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.1873. Min Act: -0.1700
Data Index: 608845 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.1248. Min Act: -0.1700
Data Index: 2731829 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.1248. Min Act: -0.1700
Data Index: 7190763 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.1248. Min Act: -0.1700
Data Index: 6943397 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.0623. Min Act: -0.1700
Data Index: 3771097 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.1248. Min Act: -0.1700
Data Index: 1431472 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.1248. Min Act: -0.1700
Data Index: 1593147 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.1248. Min Act: -0.1700
Data Index: 5698863 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.0623. Min Act: -0.1700
Data Index: 4234363 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4998. Min Range: -8.4998
Max Act: 8.0623. Min Act: -0.1700
Data Index: 2206511 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19