Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5805 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.8817. Min Act: -0.1700
Data Index: 722230 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.6584. Min Act: -0.1700
Data Index: 1738660 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.6103. Min Act: -0.1700
Data Index: 3692652 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.5942. Min Act: -0.1700
Data Index: 8430717 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.5619. Min Act: -0.1700
Data Index: 1738658 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.5619. Min Act: -0.1700
Data Index: 4118449 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.5942. Min Act: -0.1700
Data Index: 1738659 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.5458. Min Act: -0.1700
Data Index: 8079222 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.5135. Min Act: -0.1700
Data Index: 764481 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.5135. Min Act: -0.1700
Data Index: 7086244 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.4973. Min Act: -0.1700
Data Index: 7758412 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.4810. Min Act: -0.1700
Data Index: 1420596 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.4810. Min Act: -0.1700
Data Index: 7524762 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.4810. Min Act: -0.1700
Data Index: 8079232 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.4648. Min Act: -0.1700
Data Index: 6922623 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.4486. Min Act: -0.1700
Data Index: 6438857 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.4648. Min Act: -0.1700
Data Index: 6430363 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.4486. Min Act: -0.1700
Data Index: 941508 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.4648. Min Act: -0.1700
Data Index: 480334 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8817. Min Range: -2.8817
Max Act: 2.4648. Min Act: -0.1700
Data Index: 8079231 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19