Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.4449. Min Act: -0.1700
Data Index: 4029824 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.3511. Min Act: -0.1700
Data Index: 4967651 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.3199. Min Act: -0.1700
Data Index: 3707005 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.2886. Min Act: -0.1700
Data Index: 4222157 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.2574. Min Act: -0.1700
Data Index: 7278909 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.1949. Min Act: -0.1700
Data Index: 7202764 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.1636. Min Act: -0.1700
Data Index: 6249220 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.1324. Min Act: -0.1700
Data Index: 166924 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.0699. Min Act: -0.1700
Data Index: 8453273 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.0699. Min Act: -0.1700
Data Index: 8614058 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.0386. Min Act: -0.1700
Data Index: 681188 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.0386. Min Act: -0.1700
Data Index: 6225408 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.0386. Min Act: -0.1700
Data Index: 1610426 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.0386. Min Act: -0.1700
Data Index: 4469646 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.0074. Min Act: -0.1700
Data Index: 8808512 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.0074. Min Act: -0.1700
Data Index: 3400759 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4449. Min Range: -7.4449
Max Act: 7.0074. Min Act: -0.1700
Data Index: 8314026 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4449. Min Range: -7.4449
Max Act: 6.9761. Min Act: -0.1700
Data Index: 5464324 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4449. Min Range: -7.4449
Max Act: 6.9761. Min Act: -0.1700
Data Index: 8025932 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4449. Min Range: -7.4449
Max Act: 6.9449. Min Act: -0.1700
Data Index: 3595497 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19