Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2126. Min Range: -3.2126
Max Act: 3.2126. Min Act: -0.1700
Data Index: 7372587 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2126. Min Range: -3.2126
Max Act: 3.1812. Min Act: -0.1700
Data Index: 7543512 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2126. Min Range: -3.2126
Max Act: 3.1182. Min Act: -0.1700
Data Index: 7372586 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2126. Min Range: -3.2126
Max Act: 3.0393. Min Act: -0.1700
Data Index: 6563218 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2126. Min Range: -3.2126
Max Act: 3.0078. Min Act: -0.1700
Data Index: 385346 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9920. Min Act: -0.1700
Data Index: 3500894 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9761. Min Act: -0.1700
Data Index: 6490451 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9920. Min Act: -0.1700
Data Index: 2031018 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9920. Min Act: -0.1700
Data Index: 728810 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9761. Min Act: -0.1700
Data Index: 1874818 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9603. Min Act: -0.1700
Data Index: 3177040 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9603. Min Act: -0.1700
Data Index: 3107225 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9445. Min Act: -0.1700
Data Index: 8111320 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9603. Min Act: -0.1700
Data Index: 4889213 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9603. Min Act: -0.1700
Data Index: 6887496 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9287. Min Act: -0.1700
Data Index: 5736455 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9445. Min Act: -0.1700
Data Index: 4209446 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9287. Min Act: -0.1700
Data Index: 6748301 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.8970. Min Act: -0.1700
Data Index: 4927412 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2126. Min Range: -3.2126
Max Act: 2.9128. Min Act: -0.1700
Data Index: 7038518 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19