Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 99 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0210. Min Range: -4.0210
Max Act: 4.0210. Min Act: -0.1700
Data Index: 1746705 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.8334. Min Act: -0.1700
Data Index: 7103244 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.8021. Min Act: -0.1700
Data Index: 32625 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.8021. Min Act: -0.1700
Data Index: 582643 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.8334. Min Act: -0.1700
Data Index: 7260211 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.7709. Min Act: -0.1700
Data Index: 6899435 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.7396. Min Act: -0.1700
Data Index: 2534284 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.7083. Min Act: -0.1700
Data Index: 2083180 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.7083. Min Act: -0.1700
Data Index: 4076787 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.6770. Min Act: -0.1700
Data Index: 6339711 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.7083. Min Act: -0.1700
Data Index: 3196673 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.6770. Min Act: -0.1700
Data Index: 7365724 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.6457. Min Act: -0.1700
Data Index: 4232729 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.6770. Min Act: -0.1700
Data Index: 582659 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.6770. Min Act: -0.1700
Data Index: 4656115 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.6457. Min Act: -0.1700
Data Index: 2970070 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.6301. Min Act: -0.1700
Data Index: 2523446 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.6457. Min Act: -0.1700
Data Index: 582649 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.6301. Min Act: -0.1700
Data Index: 1628532 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0210. Min Range: -4.0210
Max Act: 3.6144. Min Act: -0.1700
Data Index: 1707860 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19