Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.8007. Min Act: -0.1700
Data Index: 2521368 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.7069. Min Act: -0.1700
Data Index: 4981148 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.6132. Min Act: -0.1700
Data Index: 6083579 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.5507. Min Act: -0.1700
Data Index: 476893 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4882. Min Act: -0.1700
Data Index: 7430925 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4882. Min Act: -0.1700
Data Index: 114922 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4569. Min Act: -0.1700
Data Index: 1559311 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4882. Min Act: -0.1700
Data Index: 6214715 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4257. Min Act: -0.1700
Data Index: 2330446 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4257. Min Act: -0.1700
Data Index: 8281330 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3944. Min Act: -0.1700
Data Index: 7100442 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3632. Min Act: -0.1700
Data Index: 7355612 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3632. Min Act: -0.1700
Data Index: 3219600 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3632. Min Act: -0.1700
Data Index: 4680776 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3319. Min Act: -0.1700
Data Index: 5529562 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3007. Min Act: -0.1700
Data Index: 1320855 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3007. Min Act: -0.1700
Data Index: 8087486 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3007. Min Act: -0.1700
Data Index: 7684084 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3007. Min Act: -0.1700
Data Index: 29835 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3007. Min Act: -0.1700
Data Index: 8497199 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19