Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 447 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.5570. Min Act: -0.1700
Data Index: 6828262 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.4633. Min Act: -0.1700
Data Index: 5908851 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.4633. Min Act: -0.1700
Data Index: 5254699 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.4320. Min Act: -0.1700
Data Index: 7224243 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.4008. Min Act: -0.1700
Data Index: 4026531 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.3695. Min Act: -0.1700
Data Index: 5877637 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.3695. Min Act: -0.1700
Data Index: 523596 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.2758. Min Act: -0.1700
Data Index: 827718 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.3070. Min Act: -0.1700
Data Index: 2352033 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.2758. Min Act: -0.1700
Data Index: 8472454 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.2758. Min Act: -0.1700
Data Index: 1578405 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.1508. Min Act: -0.1700
Data Index: 7509559 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.1820. Min Act: -0.1700
Data Index: 5595975 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.1820. Min Act: -0.1700
Data Index: 6443822 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.1820. Min Act: -0.1700
Data Index: 3942852 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.1508. Min Act: -0.1700
Data Index: 3962875 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.1195. Min Act: -0.1700
Data Index: 7968599 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.0883. Min Act: -0.1700
Data Index: 2755875 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.0883. Min Act: -0.1700
Data Index: 3470120 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5570. Min Range: -6.5570
Max Act: 6.0258. Min Act: -0.1700
Data Index: 3099217 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19