Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1217 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.6074. Min Act: -0.1700
Data Index: 2323682 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.5449. Min Act: -0.1700
Data Index: 8807978 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.5137. Min Act: -0.1700
Data Index: 3949243 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.5449. Min Act: -0.1700
Data Index: 7400937 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.4824. Min Act: -0.1700
Data Index: 5967654 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3262. Min Act: -0.1700
Data Index: 4217231 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3574. Min Act: -0.1700
Data Index: 7582256 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3887. Min Act: -0.1700
Data Index: 8394623 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3574. Min Act: -0.1700
Data Index: 3270480 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3574. Min Act: -0.1700
Data Index: 5719405 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3262. Min Act: -0.1700
Data Index: 163255 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3262. Min Act: -0.1700
Data Index: 5447583 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3262. Min Act: -0.1700
Data Index: 1221518 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3574. Min Act: -0.1700
Data Index: 4308601 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.2949. Min Act: -0.1700
Data Index: 2970834 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3262. Min Act: -0.1700
Data Index: 2796814 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.3262. Min Act: -0.1700
Data Index: 5398785 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.2637. Min Act: -0.1700
Data Index: 2784526 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.2949. Min Act: -0.1700
Data Index: 1062002 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6074. Min Range: -4.6074
Max Act: 4.2949. Min Act: -0.1700
Data Index: 5909063 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19