Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0772. Min Range: -6.0772
Max Act: 6.0772. Min Act: -0.1700
Data Index: 7113817 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0772. Min Range: -6.0772
Max Act: 6.0147. Min Act: -0.1700
Data Index: 1853037 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.9210. Min Act: -0.1700
Data Index: 2911006 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.9210. Min Act: -0.1700
Data Index: 654926 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.8897. Min Act: -0.1700
Data Index: 7256800 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.8585. Min Act: -0.1700
Data Index: 6169995 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.8585. Min Act: -0.1700
Data Index: 6732277 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.8585. Min Act: -0.1700
Data Index: 2274315 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.8272. Min Act: -0.1700
Data Index: 6893569 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.8272. Min Act: -0.1700
Data Index: 4957282 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.7647. Min Act: -0.1700
Data Index: 1437744 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.7647. Min Act: -0.1700
Data Index: 6765815 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.7647. Min Act: -0.1700
Data Index: 8666315 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.7335. Min Act: -0.1700
Data Index: 4633015 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.7335. Min Act: -0.1700
Data Index: 2726871 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.7022. Min Act: -0.1700
Data Index: 1680922 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.7022. Min Act: -0.1700
Data Index: 4091510 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.7022. Min Act: -0.1700
Data Index: 3579724 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.7022. Min Act: -0.1700
Data Index: 7272376 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0772. Min Range: -6.0772
Max Act: 5.6710. Min Act: -0.1700
Data Index: 6739166 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19