Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0566. Min Range: -5.0566
Max Act: 5.0566. Min Act: -0.1700
Data Index: 5500311 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.9941. Min Act: -0.1700
Data Index: 2065233 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.9629. Min Act: -0.1700
Data Index: 97049 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.9316. Min Act: -0.1700
Data Index: 4493024 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.8691. Min Act: -0.1700
Data Index: 3907670 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.8379. Min Act: -0.1700
Data Index: 3840814 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.8379. Min Act: -0.1700
Data Index: 6215075 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.8691. Min Act: -0.1700
Data Index: 2334954 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.8379. Min Act: -0.1700
Data Index: 548085 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.8066. Min Act: -0.1700
Data Index: 7678566 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.8066. Min Act: -0.1700
Data Index: 862187 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.7754. Min Act: -0.1700
Data Index: 1837790 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.7129. Min Act: -0.1700
Data Index: 5463633 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.7441. Min Act: -0.1700
Data Index: 2861103 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.7754. Min Act: -0.1700
Data Index: 6306307 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.7441. Min Act: -0.1700
Data Index: 6196979 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.7441. Min Act: -0.1700
Data Index: 956009 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.7441. Min Act: -0.1700
Data Index: 2787603 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.7129. Min Act: -0.1700
Data Index: 4630678 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0566. Min Range: -5.0566
Max Act: 4.7129. Min Act: -0.1700
Data Index: 1805047 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19