Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2792 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4795. Min Range: -5.4795
Max Act: 5.4795. Min Act: -0.1700
Data Index: 3968863 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4795. Min Range: -5.4795
Max Act: 5.0732. Min Act: -0.1700
Data Index: 1896631 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4795. Min Range: -5.4795
Max Act: 5.0420. Min Act: -0.1700
Data Index: 5414996 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4795. Min Range: -5.4795
Max Act: 5.0107. Min Act: -0.1700
Data Index: 5749444 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.9482. Min Act: -0.1700
Data Index: 5531395 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.9482. Min Act: -0.1700
Data Index: 5710742 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.9795. Min Act: -0.1700
Data Index: 7982146 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.9482. Min Act: -0.1700
Data Index: 1246613 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.9482. Min Act: -0.1700
Data Index: 8564921 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.9170. Min Act: -0.1700
Data Index: 6761918 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.8857. Min Act: -0.1700
Data Index: 2702188 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.8545. Min Act: -0.1700
Data Index: 2278029 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.8545. Min Act: -0.1700
Data Index: 4492767 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.8545. Min Act: -0.1700
Data Index: 7031032 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.8545. Min Act: -0.1700
Data Index: 2917628 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.8545. Min Act: -0.1700
Data Index: 4832723 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.8545. Min Act: -0.1700
Data Index: 7540192 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.8232. Min Act: -0.1700
Data Index: 1206512 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.8232. Min Act: -0.1700
Data Index: 3712626 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4795. Min Range: -5.4795
Max Act: 4.8232. Min Act: -0.1700
Data Index: 7068985 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19