Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2576 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.9253. Min Act: -0.1700
Data Index: 462065 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.9253. Min Act: -0.1700
Data Index: 3472831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.9253. Min Act: -0.1700
Data Index: 7806612 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8940. Min Act: -0.1700
Data Index: 1977612 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8940. Min Act: -0.1700
Data Index: 4758460 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8940. Min Act: -0.1700
Data Index: 6834048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8315. Min Act: -0.1700
Data Index: 5897772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8627. Min Act: -0.1700
Data Index: 4730461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8627. Min Act: -0.1700
Data Index: 8804816 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8315. Min Act: -0.1700
Data Index: 1526440 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8315. Min Act: -0.1700
Data Index: 4309416 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8315. Min Act: -0.1700
Data Index: 6130115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8315. Min Act: -0.1700
Data Index: 5919175 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8315. Min Act: -0.1700
Data Index: 5482689 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8315. Min Act: -0.1700
Data Index: 2670661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8002. Min Act: -0.1700
Data Index: 3900176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8002. Min Act: -0.1700
Data Index: 1723563 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8002. Min Act: -0.1700
Data Index: 4309803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8002. Min Act: -0.1700
Data Index: 1894681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9253. Min Range: -3.9253
Max Act: 3.8002. Min Act: -0.1700
Data Index: 4827731 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19