Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1960 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.4569. Min Act: -0.1700
Data Index: 1339910 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.4412. Min Act: -0.1700
Data Index: 4272425 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.3628. Min Act: -0.1700
Data Index: 7868680 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.3628. Min Act: -0.1700
Data Index: 6381225 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.3000. Min Act: -0.1700
Data Index: 8198366 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.3000. Min Act: -0.1700
Data Index: 1749219 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.2372. Min Act: -0.1700
Data Index: 339282 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.2215. Min Act: -0.1700
Data Index: 1601969 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.2058. Min Act: -0.1700
Data Index: 2581984 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1586. Min Act: -0.1700
Data Index: 2052529 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1586. Min Act: -0.1700
Data Index: 5441126 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1586. Min Act: -0.1700
Data Index: 1998222 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1586. Min Act: -0.1700
Data Index: 8281175 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1586. Min Act: -0.1700
Data Index: 1329711 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1271. Min Act: -0.1700
Data Index: 8766553 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1271. Min Act: -0.1700
Data Index: 4865899 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1271. Min Act: -0.1700
Data Index: 1083074 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0956. Min Act: -0.1700
Data Index: 4847203 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0956. Min Act: -0.1700
Data Index: 6630211 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0640. Min Act: -0.1700
Data Index: 8794842 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19