Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4100 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2481. Min Act: -0.0002

Data Index: 1230005 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2384. Min Act: -0.0002

Data Index: 447920 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2307. Min Act: -0.0002

Data Index: 296808 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2276. Min Act: -0.0002

Data Index: 1131901 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2209. Min Act: -0.0002

Data Index: 147834 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2172. Min Act: -0.0002

Data Index: 133284 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2096. Min Act: -0.0002

Data Index: 1061034 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2051. Min Act: -0.0002

Data Index: 794369 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2043. Min Act: -0.0002

Data Index: 482889 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2093. Min Act: -0.0002

Data Index: 856842 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2037. Min Act: -0.0002

Data Index: 551172 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2067. Min Act: -0.0002

Data Index: 1299194 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2048. Min Act: -0.0003

Data Index: 161835 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2026. Min Act: -0.0002

Data Index: 258412 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2025. Min Act: -0.0002

Data Index: 205834 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2046. Min Act: -0.0002

Data Index: 202785 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2021. Min Act: -0.0002

Data Index: 565351 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2006. Min Act: -0.0002

Data Index: 810814 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2044. Min Act: -0.0002

Data Index: 24282 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2062. Min Act: -0.0002

Data Index: 217305 (C4 (Web Text))

Max Activating Token Index: 680