Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 347 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0596. Min Range: -6.0596
Max Act: 6.0596. Min Act: -0.1700
Data Index: 4584037 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.5909. Min Act: -0.1700
Data Index: 3420288 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.4034. Min Act: -0.1700
Data Index: 7672441 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.4034. Min Act: -0.1700
Data Index: 2252816 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.2471. Min Act: -0.1700
Data Index: 1663873 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.2471. Min Act: -0.1700
Data Index: 4900264 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.2784. Min Act: -0.1700
Data Index: 6605009 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.2159. Min Act: -0.1700
Data Index: 1626038 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.1534. Min Act: -0.1700
Data Index: 760168 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.1534. Min Act: -0.1700
Data Index: 3581055 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.1221. Min Act: -0.1700
Data Index: 5599673 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.0909. Min Act: -0.1700
Data Index: 545075 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.0909. Min Act: -0.1700
Data Index: 7348871 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.0909. Min Act: -0.1700
Data Index: 4441651 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.0909. Min Act: -0.1700
Data Index: 5278179 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.0596. Min Act: -0.1700
Data Index: 5913911 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0596. Min Range: -6.0596
Max Act: 4.9971. Min Act: -0.1700
Data Index: 4350335 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0596. Min Range: -6.0596
Max Act: 5.0284. Min Act: -0.1700
Data Index: 6865463 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0596. Min Range: -6.0596
Max Act: 4.9971. Min Act: -0.1700
Data Index: 1051024 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0596. Min Range: -6.0596
Max Act: 4.9971. Min Act: -0.1700
Data Index: 687542 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19