Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.7363. Min Act: -0.1700
Data Index: 6396562 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.7363. Min Act: -0.1700
Data Index: 7308245 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.7203. Min Act: -0.1700
Data Index: 4893916 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.6723. Min Act: -0.1700
Data Index: 7018069 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.6883. Min Act: -0.1700
Data Index: 1007317 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.6563. Min Act: -0.1700
Data Index: 3396346 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.6563. Min Act: -0.1700
Data Index: 3440266 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.6563. Min Act: -0.1700
Data Index: 6935601 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.6241. Min Act: -0.1700
Data Index: 4814005 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.6081. Min Act: -0.1700
Data Index: 262572 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.6081. Min Act: -0.1700
Data Index: 3512333 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.5759. Min Act: -0.1700
Data Index: 2806096 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.5920. Min Act: -0.1700
Data Index: 281881 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.5920. Min Act: -0.1700
Data Index: 7264020 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.5597. Min Act: -0.1700
Data Index: 1793654 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.5920. Min Act: -0.1700
Data Index: 4893385 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.5759. Min Act: -0.1700
Data Index: 8654281 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.5920. Min Act: -0.1700
Data Index: 5334388 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.5597. Min Act: -0.1700
Data Index: 6355902 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7363. Min Range: -2.7363
Max Act: 2.5759. Min Act: -0.1700
Data Index: 1955004 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19