Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 912 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1958. Min Range: -7.1958
Max Act: 7.1958. Min Act: -0.1700
Data Index: 5986172 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1958. Min Range: -7.1958
Max Act: 7.0396. Min Act: -0.1700
Data Index: 6393886 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1958. Min Range: -7.1958
Max Act: 7.0708. Min Act: -0.1700
Data Index: 7669349 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.9771. Min Act: -0.1700
Data Index: 973332 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.9146. Min Act: -0.1700
Data Index: 4506137 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.9146. Min Act: -0.1700
Data Index: 2806809 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.9146. Min Act: -0.1700
Data Index: 549693 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.8833. Min Act: -0.1700
Data Index: 5962855 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.8833. Min Act: -0.1700
Data Index: 8225972 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.8208. Min Act: -0.1700
Data Index: 7836483 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.8521. Min Act: -0.1700
Data Index: 8621628 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.8521. Min Act: -0.1700
Data Index: 5244690 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.8208. Min Act: -0.1700
Data Index: 912615 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.7583. Min Act: -0.1700
Data Index: 2112787 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.7583. Min Act: -0.1700
Data Index: 3880989 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.7271. Min Act: -0.1700
Data Index: 8671378 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.6958. Min Act: -0.1700
Data Index: 3688759 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.7271. Min Act: -0.1700
Data Index: 8765448 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.7271. Min Act: -0.1700
Data Index: 2303228 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.6958. Min Act: -0.1700
Data Index: 1973197 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19