Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.3894. Min Act: -0.1700
Data Index: 7215298 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.3269. Min Act: -0.1700
Data Index: 3940837 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.2957. Min Act: -0.1700
Data Index: 8632563 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.1394. Min Act: -0.1700
Data Index: 7630174 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.1394. Min Act: -0.1700
Data Index: 5590127 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.0769. Min Act: -0.1700
Data Index: 2792098 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.0769. Min Act: -0.1700
Data Index: 7326157 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.1082. Min Act: -0.1700
Data Index: 1080581 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.0457. Min Act: -0.1700
Data Index: 2792105 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.0769. Min Act: -0.1700
Data Index: 3869287 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3894. Min Range: -6.3894
Max Act: 6.0144. Min Act: -0.1700
Data Index: 3253068 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3894. Min Range: -6.3894
Max Act: 5.9832. Min Act: -0.1700
Data Index: 4152981 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3894. Min Range: -6.3894
Max Act: 5.9832. Min Act: -0.1700
Data Index: 7124433 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3894. Min Range: -6.3894
Max Act: 5.9207. Min Act: -0.1700
Data Index: 7805371 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3894. Min Range: -6.3894
Max Act: 5.8894. Min Act: -0.1700
Data Index: 4106947 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3894. Min Range: -6.3894
Max Act: 5.8894. Min Act: -0.1700
Data Index: 5193062 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3894. Min Range: -6.3894
Max Act: 5.9207. Min Act: -0.1700
Data Index: 3162459 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3894. Min Range: -6.3894
Max Act: 5.8894. Min Act: -0.1700
Data Index: 7702372 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3894. Min Range: -6.3894
Max Act: 5.8894. Min Act: -0.1700
Data Index: 5319302 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3894. Min Range: -6.3894
Max Act: 5.8269. Min Act: -0.1700
Data Index: 5132581 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19