Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2936. Min Range: -6.2936
Max Act: 6.2936. Min Act: -0.1700
Data Index: 6736924 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.6998. Min Act: -0.1700
Data Index: 5516579 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.5436. Min Act: -0.1700
Data Index: 7129310 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4498. Min Act: -0.1700
Data Index: 4494256 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4498. Min Act: -0.1700
Data Index: 1578631 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4498. Min Act: -0.1700
Data Index: 2792973 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4186. Min Act: -0.1700
Data Index: 329577 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4186. Min Act: -0.1700
Data Index: 280249 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4186. Min Act: -0.1700
Data Index: 1417920 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.3873. Min Act: -0.1700
Data Index: 1412656 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.3248. Min Act: -0.1700
Data Index: 4848621 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.3248. Min Act: -0.1700
Data Index: 8041889 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.3248. Min Act: -0.1700
Data Index: 3148984 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.3248. Min Act: -0.1700
Data Index: 682252 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.3248. Min Act: -0.1700
Data Index: 2146559 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.2936. Min Act: -0.1700
Data Index: 6985088 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.2623. Min Act: -0.1700
Data Index: 8255777 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.2623. Min Act: -0.1700
Data Index: 2720853 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.1998. Min Act: -0.1700
Data Index: 4266953 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.1686. Min Act: -0.1700
Data Index: 3324062 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19