Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3905 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.3356. Min Act: -0.1700
Data Index: 461794 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.1794. Min Act: -0.1700
Data Index: 2015805 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.1481. Min Act: -0.1700
Data Index: 5347443 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.1481. Min Act: -0.1700
Data Index: 202591 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.1169. Min Act: -0.1700
Data Index: 2967254 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.1169. Min Act: -0.1700
Data Index: 8785855 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.1169. Min Act: -0.1700
Data Index: 7326231 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0856. Min Act: -0.1700
Data Index: 7720357 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0856. Min Act: -0.1700
Data Index: 6969366 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0856. Min Act: -0.1700
Data Index: 5347436 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0856. Min Act: -0.1700
Data Index: 3716462 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0544. Min Act: -0.1700
Data Index: 4601929 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0231. Min Act: -0.1700
Data Index: 1212573 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0544. Min Act: -0.1700
Data Index: 7109297 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0544. Min Act: -0.1700
Data Index: 107041 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0231. Min Act: -0.1700
Data Index: 5347448 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0231. Min Act: -0.1700
Data Index: 8622898 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0231. Min Act: -0.1700
Data Index: 3201980 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0231. Min Act: -0.1700
Data Index: 2073935 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3356. Min Range: -5.3356
Max Act: 5.0231. Min Act: -0.1700
Data Index: 5347442 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19