Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5950 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.7002. Min Act: -0.1700
Data Index: 730499 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.5752. Min Act: -0.1700
Data Index: 2226314 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.4502. Min Act: -0.1700
Data Index: 690833 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.4190. Min Act: -0.1700
Data Index: 8669316 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.3877. Min Act: -0.1700
Data Index: 4043869 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.3565. Min Act: -0.1700
Data Index: 3839067 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.3252. Min Act: -0.1700
Data Index: 261591 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2940. Min Act: -0.1700
Data Index: 5666639 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2940. Min Act: -0.1700
Data Index: 8442683 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2315. Min Act: -0.1700
Data Index: 6518730 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2627. Min Act: -0.1700
Data Index: 2025808 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2315. Min Act: -0.1700
Data Index: 6168893 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2315. Min Act: -0.1700
Data Index: 8765495 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2315. Min Act: -0.1700
Data Index: 2129941 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2315. Min Act: -0.1700
Data Index: 8717442 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2315. Min Act: -0.1700
Data Index: 437856 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2002. Min Act: -0.1700
Data Index: 5884124 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.2002. Min Act: -0.1700
Data Index: 2806422 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.1690. Min Act: -0.1700
Data Index: 3654456 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7002. Min Range: -6.7002
Max Act: 6.1690. Min Act: -0.1700
Data Index: 912757 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19