Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4977 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.1860. Min Act: -0.0000

Data Index: 1123246 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.2198. Min Act: -0.0000

Data Index: 62251 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.2000. Min Act: -0.0000

Data Index: 516531 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.1681. Min Act: -0.0000

Data Index: 296133 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.1511. Min Act: -0.0000

Data Index: 109623 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0973. Min Act: -0.0000

Data Index: 949151 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.1620. Min Act: -0.0000

Data Index: 72851 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0267. Min Act: -0.0000

Data Index: 374577 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0275. Min Act: -0.0000

Data Index: 134668 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0574. Min Act: -0.0000

Data Index: 323738 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1052215 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0178. Min Act: -0.0000

Data Index: 574817 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0953. Min Act: -0.0000

Data Index: 1140838 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0596. Min Act: -0.0000

Data Index: 56633 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1211944 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1351543 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0249. Min Act: -0.0000

Data Index: 569428 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9621. Min Act: -0.0000

Data Index: 130679 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8741. Min Act: -0.0000

Data Index: 103030 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0224. Min Act: -0.0000

Data Index: 691057 (C4 (Web Text))

Max Activating Token Index: 956