Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1891 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.4553. Min Act: -0.1700
Data Index: 5553245 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.4241. Min Act: -0.1700
Data Index: 4761270 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.3928. Min Act: -0.1700
Data Index: 7151653 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.4553. Min Act: -0.1700
Data Index: 61722 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.3616. Min Act: -0.1700
Data Index: 4933546 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.3616. Min Act: -0.1700
Data Index: 7857101 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.3928. Min Act: -0.1700
Data Index: 1162989 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.3928. Min Act: -0.1700
Data Index: 3816815 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.2678. Min Act: -0.1700
Data Index: 6230637 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.3303. Min Act: -0.1700
Data Index: 1977322 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.3303. Min Act: -0.1700
Data Index: 4824399 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.2678. Min Act: -0.1700
Data Index: 7869113 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.3303. Min Act: -0.1700
Data Index: 5474651 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.3303. Min Act: -0.1700
Data Index: 3011831 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.3303. Min Act: -0.1700
Data Index: 2850952 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.2991. Min Act: -0.1700
Data Index: 6446882 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.2991. Min Act: -0.1700
Data Index: 4805576 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.2991. Min Act: -0.1700
Data Index: 6189169 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.2678. Min Act: -0.1700
Data Index: 5601616 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4553. Min Range: -4.4553
Max Act: 4.2991. Min Act: -0.1700
Data Index: 4531575 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19