Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4856 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0111. Min Range: -3.0111
Max Act: 3.0111. Min Act: -0.1700
Data Index: 6425455 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8686. Min Act: -0.1700
Data Index: 3757849 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8686. Min Act: -0.1700
Data Index: 8191516 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8527. Min Act: -0.1700
Data Index: 4292029 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8686. Min Act: -0.1700
Data Index: 8573064 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8527. Min Act: -0.1700
Data Index: 740993 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8527. Min Act: -0.1700
Data Index: 6171174 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8686. Min Act: -0.1700
Data Index: 1089051 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8368. Min Act: -0.1700
Data Index: 4703933 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8527. Min Act: -0.1700
Data Index: 6022911 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8209. Min Act: -0.1700
Data Index: 1281314 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8209. Min Act: -0.1700
Data Index: 5913933 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8368. Min Act: -0.1700
Data Index: 3232679 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8209. Min Act: -0.1700
Data Index: 3769048 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8209. Min Act: -0.1700
Data Index: 157831 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8209. Min Act: -0.1700
Data Index: 7585624 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.7890. Min Act: -0.1700
Data Index: 2589180 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.8050. Min Act: -0.1700
Data Index: 2427968 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.7890. Min Act: -0.1700
Data Index: 6986385 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0111. Min Range: -3.0111
Max Act: 2.7890. Min Act: -0.1700
Data Index: 6497581 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19