Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4511 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.8066. Min Act: -0.1700
Data Index: 4451713 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.7747. Min Act: -0.1700
Data Index: 5592261 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.7588. Min Act: -0.1700
Data Index: 3918356 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.7428. Min Act: -0.1700
Data Index: 3341046 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.7109. Min Act: -0.1700
Data Index: 1287814 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.7109. Min Act: -0.1700
Data Index: 6656722 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6949. Min Act: -0.1700
Data Index: 87166 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6789. Min Act: -0.1700
Data Index: 6583581 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6789. Min Act: -0.1700
Data Index: 1459530 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6949. Min Act: -0.1700
Data Index: 6679930 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6307. Min Act: -0.1700
Data Index: 573617 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6307. Min Act: -0.1700
Data Index: 8824533 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6307. Min Act: -0.1700
Data Index: 4667090 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6147. Min Act: -0.1700
Data Index: 1425875 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6307. Min Act: -0.1700
Data Index: 323689 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6147. Min Act: -0.1700
Data Index: 6301722 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.5986. Min Act: -0.1700
Data Index: 4115315 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.6147. Min Act: -0.1700
Data Index: 2800408 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.5986. Min Act: -0.1700
Data Index: 1996293 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8066. Min Range: -2.8066
Max Act: 2.5986. Min Act: -0.1700
Data Index: 4594726 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19