Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2047 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.4054. Min Act: -0.0001

Data Index: 358910 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2606. Min Act: -0.0001

Data Index: 301190 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2185. Min Act: -0.0001

Data Index: 468247 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1238. Min Act: -0.0001

Data Index: 921825 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9439. Min Act: -0.0001

Data Index: 292739 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9602. Min Act: -0.0001

Data Index: 1017170 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9585. Min Act: -0.0001

Data Index: 979939 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9412. Min Act: -0.0001

Data Index: 165782 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8107. Min Act: -0.0001

Data Index: 996275 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8513. Min Act: -0.0001

Data Index: 206283 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8360. Min Act: -0.0001

Data Index: 864701 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8469. Min Act: -0.0001

Data Index: 238113 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9216. Min Act: -0.0001

Data Index: 1077491 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8833. Min Act: -0.0001

Data Index: 172829 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8263. Min Act: -0.0001

Data Index: 318892 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8191. Min Act: -0.0001

Data Index: 831213 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.7289. Min Act: -0.0001

Data Index: 394261 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.7017. Min Act: -0.0001

Data Index: 234443 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.7240. Min Act: -0.0001

Data Index: 448577 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.7677. Min Act: -0.0001

Data Index: 386659 (C4 (Web Text))

Max Activating Token Index: 452