Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.7548. Min Act: -0.1700
Data Index: 5966683 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.7236. Min Act: -0.1700
Data Index: 4132524 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.6298. Min Act: -0.1700
Data Index: 2006045 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.5986. Min Act: -0.1700
Data Index: 6586634 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.5986. Min Act: -0.1700
Data Index: 8601949 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.5673. Min Act: -0.1700
Data Index: 391578 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.5361. Min Act: -0.1700
Data Index: 5079242 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.5361. Min Act: -0.1700
Data Index: 6374709 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.5048. Min Act: -0.1700
Data Index: 3347991 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.4736. Min Act: -0.1700
Data Index: 4941487 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.4736. Min Act: -0.1700
Data Index: 13475 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.4736. Min Act: -0.1700
Data Index: 2571483 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.4736. Min Act: -0.1700
Data Index: 6295341 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.4423. Min Act: -0.1700
Data Index: 816642 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.4423. Min Act: -0.1700
Data Index: 1102963 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.4111. Min Act: -0.1700
Data Index: 5079243 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.4111. Min Act: -0.1700
Data Index: 4576346 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3798. Min Act: -0.1700
Data Index: 6664509 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3798. Min Act: -0.1700
Data Index: 140677 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.3798. Min Act: -0.1700
Data Index: 6059657 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19