Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.6860. Min Act: -0.1700
Data Index: 7163615 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.6860. Min Act: -0.1700
Data Index: 8333292 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.6235. Min Act: -0.1700
Data Index: 67831 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.5610. Min Act: -0.1700
Data Index: 6553894 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.5298. Min Act: -0.1700
Data Index: 793061 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.6235. Min Act: -0.1700
Data Index: 5525375 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.5610. Min Act: -0.1700
Data Index: 7593389 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.5298. Min Act: -0.1700
Data Index: 4725900 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.5610. Min Act: -0.1700
Data Index: 2065705 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.5298. Min Act: -0.1700
Data Index: 7683997 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.5298. Min Act: -0.1700
Data Index: 4177238 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.4985. Min Act: -0.1700
Data Index: 3041474 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.4985. Min Act: -0.1700
Data Index: 8765846 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.4673. Min Act: -0.1700
Data Index: 5598128 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.4673. Min Act: -0.1700
Data Index: 3915999 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.4673. Min Act: -0.1700
Data Index: 6657861 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.4360. Min Act: -0.1700
Data Index: 692592 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.4048. Min Act: -0.1700
Data Index: 889540 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.4673. Min Act: -0.1700
Data Index: 4477054 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6860. Min Range: -6.6860
Max Act: 6.4048. Min Act: -0.1700
Data Index: 5123501 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19