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

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

Neuron 4843 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: 3.5187. Min Range: -3.5187

Max Act: 3.5187. Min Act: -0.0000

Data Index: 64346 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 3.5187. Min Range: -3.5187

Max Act: 3.2512. Min Act: -0.0000

Data Index: 705040 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 3.5187. Min Range: -3.5187

Max Act: 3.1088. Min Act: -0.0000

Data Index: 479685 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 3.5187. Min Range: -3.5187

Max Act: 3.0769. Min Act: -0.0000

Data Index: 860264 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 3.5187. Min Range: -3.5187

Max Act: 3.0958. Min Act: -0.0000

Data Index: 199857 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.8989. Min Act: -0.0000

Data Index: 12623 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 3.5187. Min Range: -3.5187

Max Act: 3.1666. Min Act: -0.0000

Data Index: 1294217 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 3.5187. Min Range: -3.5187

Max Act: 3.1610. Min Act: -0.0000

Data Index: 1134392 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.9980. Min Act: -0.0000

Data Index: 501236 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.8491. Min Act: -0.0000

Data Index: 914114 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.8380. Min Act: -0.0000

Data Index: 471944 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.8062. Min Act: -0.0000

Data Index: 1229937 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.8061. Min Act: -0.0000

Data Index: 20715 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.7898. Min Act: -0.0000

Data Index: 1063069 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.5162. Min Act: -0.0000

Data Index: 392392 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.9246. Min Act: -0.0000

Data Index: 1253614 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.7264. Min Act: -0.0000

Data Index: 137709 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.7337. Min Act: -0.0000

Data Index: 1011812 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.5020. Min Act: -0.0000

Data Index: 268031 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 3.5187. Min Range: -3.5187

Max Act: 2.8134. Min Act: -0.0000

Data Index: 817557 (C4 (Web Text))

Max Activating Token Index: 431