Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3907 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.9372. Min Act: -0.1700
Data Index: 3380073 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.9059. Min Act: -0.1700
Data Index: 3967754 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.8747. Min Act: -0.1700
Data Index: 6525859 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.8434. Min Act: -0.1700
Data Index: 6258684 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.8122. Min Act: -0.1700
Data Index: 7590366 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.7497. Min Act: -0.1700
Data Index: 1854230 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.7497. Min Act: -0.1700
Data Index: 2563888 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.7184. Min Act: -0.1700
Data Index: 4653355 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.6872. Min Act: -0.1700
Data Index: 5249235 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.6559. Min Act: -0.1700
Data Index: 4567952 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.6247. Min Act: -0.1700
Data Index: 5397761 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.5622. Min Act: -0.1700
Data Index: 7908670 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.5309. Min Act: -0.1700
Data Index: 1080639 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.5309. Min Act: -0.1700
Data Index: 4416233 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.4997. Min Act: -0.1700
Data Index: 6882140 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.4997. Min Act: -0.1700
Data Index: 2038542 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.4997. Min Act: -0.1700
Data Index: 4952778 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.4997. Min Act: -0.1700
Data Index: 3210026 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.4997. Min Act: -0.1700
Data Index: 5399994 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9372. Min Range: -6.9372
Max Act: 6.4372. Min Act: -0.1700
Data Index: 4117482 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19