Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1595 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2774. Min Range: -8.2774
Max Act: 8.2774. Min Act: -0.1700
Data Index: 6060097 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.7461. Min Act: -0.1700
Data Index: 4313681 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.7149. Min Act: -0.1700
Data Index: 4480637 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.6524. Min Act: -0.1700
Data Index: 3403689 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.6524. Min Act: -0.1700
Data Index: 4488695 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4961. Min Act: -0.1700
Data Index: 5276398 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4336. Min Act: -0.1700
Data Index: 6651527 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4649. Min Act: -0.1700
Data Index: 6659310 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4961. Min Act: -0.1700
Data Index: 3142193 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4336. Min Act: -0.1700
Data Index: 2661953 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4024. Min Act: -0.1700
Data Index: 6821378 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4024. Min Act: -0.1700
Data Index: 1328153 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4336. Min Act: -0.1700
Data Index: 4982337 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.3711. Min Act: -0.1700
Data Index: 6909841 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.3399. Min Act: -0.1700
Data Index: 1666870 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4024. Min Act: -0.1700
Data Index: 6762436 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4024. Min Act: -0.1700
Data Index: 569233 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.3399. Min Act: -0.1700
Data Index: 4847635 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.4024. Min Act: -0.1700
Data Index: 3327945 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2774. Min Range: -8.2774
Max Act: 7.3399. Min Act: -0.1700
Data Index: 1408002 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19