Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1963 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.4583. Min Act: -0.1700
Data Index: 6545768 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.4583. Min Act: -0.1700
Data Index: 5117357 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.4271. Min Act: -0.1700
Data Index: 335723 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.4271. Min Act: -0.1700
Data Index: 1215666 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.3958. Min Act: -0.1700
Data Index: 4458819 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.3646. Min Act: -0.1700
Data Index: 3041770 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.2083. Min Act: -0.1700
Data Index: 7447429 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.1771. Min Act: -0.1700
Data Index: 2356380 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.1146. Min Act: -0.1700
Data Index: 3659414 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.1146. Min Act: -0.1700
Data Index: 4363535 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.0833. Min Act: -0.1700
Data Index: 6488394 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.1146. Min Act: -0.1700
Data Index: 3156466 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.0833. Min Act: -0.1700
Data Index: 5127803 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.0521. Min Act: -0.1700
Data Index: 7487592 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.0521. Min Act: -0.1700
Data Index: 8087276 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.0521. Min Act: -0.1700
Data Index: 2584523 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.0521. Min Act: -0.1700
Data Index: 5546900 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.0521. Min Act: -0.1700
Data Index: 297357 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4583. Min Range: -6.4583
Max Act: 6.0208. Min Act: -0.1700
Data Index: 3272820 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4583. Min Range: -6.4583
Max Act: 5.9896. Min Act: -0.1700
Data Index: 6545767 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19