Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.6194. Min Act: -0.1700
Data Index: 8151439 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.3381. Min Act: -0.1700
Data Index: 6991498 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.1506. Min Act: -0.1700
Data Index: 3309553 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.1819. Min Act: -0.1700
Data Index: 1202385 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.0569. Min Act: -0.1700
Data Index: 8292570 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.0569. Min Act: -0.1700
Data Index: 5754739 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.0256. Min Act: -0.1700
Data Index: 3377867 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.0256. Min Act: -0.1700
Data Index: 8641057 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.9944. Min Act: -0.1700
Data Index: 5335126 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.9631. Min Act: -0.1700
Data Index: 3138894 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.9631. Min Act: -0.1700
Data Index: 844351 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.9631. Min Act: -0.1700
Data Index: 8641055 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.9319. Min Act: -0.1700
Data Index: 1087255 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.9006. Min Act: -0.1700
Data Index: 3309554 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.8694. Min Act: -0.1700
Data Index: 5076534 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.8694. Min Act: -0.1700
Data Index: 3309556 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.8381. Min Act: -0.1700
Data Index: 3082753 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.8069. Min Act: -0.1700
Data Index: 4984354 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.7756. Min Act: -0.1700
Data Index: 8144418 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6194. Min Range: -5.6194
Max Act: 4.8069. Min Act: -0.1700
Data Index: 473327 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19