Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1992 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0147. Min Range: -5.0147
Max Act: 5.0147. Min Act: -0.1700
Data Index: 5041987 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.8584. Min Act: -0.1700
Data Index: 199528 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.7959. Min Act: -0.1700
Data Index: 7778901 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.7959. Min Act: -0.1700
Data Index: 8778663 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.7959. Min Act: -0.1700
Data Index: 7767115 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.7022. Min Act: -0.1700
Data Index: 201169 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.6709. Min Act: -0.1700
Data Index: 1134522 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.6709. Min Act: -0.1700
Data Index: 6469850 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.7022. Min Act: -0.1700
Data Index: 4809943 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.6709. Min Act: -0.1700
Data Index: 6768896 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.6397. Min Act: -0.1700
Data Index: 6343296 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.6084. Min Act: -0.1700
Data Index: 7904767 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.6397. Min Act: -0.1700
Data Index: 1936074 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.5459. Min Act: -0.1700
Data Index: 7959325 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.5772. Min Act: -0.1700
Data Index: 4558483 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.5459. Min Act: -0.1700
Data Index: 5194084 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.5772. Min Act: -0.1700
Data Index: 1766272 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.5772. Min Act: -0.1700
Data Index: 5147950 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.5772. Min Act: -0.1700
Data Index: 7113446 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0147. Min Range: -5.0147
Max Act: 4.5459. Min Act: -0.1700
Data Index: 1701400 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19