Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2064. Min Range: -4.2064
Max Act: 4.2064. Min Act: -0.1700
Data Index: 755617 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2064. Min Range: -4.2064
Max Act: 4.0501. Min Act: -0.1700
Data Index: 3488431 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.9250. Min Act: -0.1700
Data Index: 1535192 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.9250. Min Act: -0.1700
Data Index: 755616 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.9250. Min Act: -0.1700
Data Index: 8345897 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.8312. Min Act: -0.1700
Data Index: 1136173 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.7687. Min Act: -0.1700
Data Index: 8210256 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.8000. Min Act: -0.1700
Data Index: 755614 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.7843. Min Act: -0.1700
Data Index: 1191704 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.7843. Min Act: -0.1700
Data Index: 6742887 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.7531. Min Act: -0.1700
Data Index: 1035101 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.7374. Min Act: -0.1700
Data Index: 3649172 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.7218. Min Act: -0.1700
Data Index: 4815844 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.6905. Min Act: -0.1700
Data Index: 2374972 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.6905. Min Act: -0.1700
Data Index: 5368094 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.6748. Min Act: -0.1700
Data Index: 755615 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.6748. Min Act: -0.1700
Data Index: 196083 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.6748. Min Act: -0.1700
Data Index: 4815845 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.6592. Min Act: -0.1700
Data Index: 5964908 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2064. Min Range: -4.2064
Max Act: 3.6592. Min Act: -0.1700
Data Index: 941506 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19