Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2103 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7042. Min Range: -3.7042
Max Act: 3.7042. Min Act: -0.1700
Data Index: 2734922 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.7596. Min Act: -0.1700
Data Index: 2725446 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.7755. Min Act: -0.1700
Data Index: 3240737 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.7117. Min Act: -0.1700
Data Index: 6952230 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.7276. Min Act: -0.1700
Data Index: 8133895 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.7276. Min Act: -0.1700
Data Index: 7571069 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6957. Min Act: -0.1700
Data Index: 3522231 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.7117. Min Act: -0.1700
Data Index: 7484966 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6957. Min Act: -0.1700
Data Index: 445956 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6797. Min Act: -0.1700
Data Index: 4508554 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.7117. Min Act: -0.1700
Data Index: 6219843 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6797. Min Act: -0.1700
Data Index: 3775952 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6797. Min Act: -0.1700
Data Index: 8260388 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6476. Min Act: -0.1700
Data Index: 7556111 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6636. Min Act: -0.1700
Data Index: 4468946 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6636. Min Act: -0.1700
Data Index: 1757582 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6636. Min Act: -0.1700
Data Index: 572546 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6476. Min Act: -0.1700
Data Index: 987127 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6476. Min Act: -0.1700
Data Index: 1680795 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7042. Min Range: -3.7042
Max Act: 2.6636. Min Act: -0.1700
Data Index: 5079321 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19