Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1521 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.4450. Min Act: -0.1700
Data Index: 7685750 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.0387. Min Act: -0.1700
Data Index: 6294186 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.0387. Min Act: -0.1700
Data Index: 3399993 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.0074. Min Act: -0.1700
Data Index: 7895323 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9762. Min Act: -0.1700
Data Index: 5488061 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9762. Min Act: -0.1700
Data Index: 4559858 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9137. Min Act: -0.1700
Data Index: 300608 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9137. Min Act: -0.1700
Data Index: 6802326 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9449. Min Act: -0.1700
Data Index: 5773592 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9137. Min Act: -0.1700
Data Index: 7594986 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9137. Min Act: -0.1700
Data Index: 8609456 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.8824. Min Act: -0.1700
Data Index: 7921438 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9137. Min Act: -0.1700
Data Index: 4770788 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.8824. Min Act: -0.1700
Data Index: 1907556 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.8824. Min Act: -0.1700
Data Index: 7694259 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.8824. Min Act: -0.1700
Data Index: 1275432 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.8824. Min Act: -0.1700
Data Index: 1166412 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.8824. Min Act: -0.1700
Data Index: 6190970 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.8511. Min Act: -0.1700
Data Index: 3073441 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.8511. Min Act: -0.1700
Data Index: 2931838 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19