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

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

Neuron 5209 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: 1.6268. Min Range: -1.6268

Max Act: 1.6268. Min Act: -0.0002

Data Index: 167852 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5318. Min Act: -0.0002

Data Index: 1156177 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.4533. Min Act: -0.0002

Data Index: 1141351 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.4561. Min Act: -0.0002

Data Index: 938063 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.3171. Min Act: -0.0002

Data Index: 86683 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2799. Min Act: -0.0002

Data Index: 114824 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2549. Min Act: -0.0002

Data Index: 585340 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.3126. Min Act: -0.0002

Data Index: 1223122 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.3126. Min Act: -0.0002

Data Index: 607345 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2328. Min Act: -0.0002

Data Index: 817572 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2365. Min Act: -0.0002

Data Index: 657477 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2384. Min Act: -0.0002

Data Index: 471774 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2625. Min Act: -0.0002

Data Index: 548094 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2101. Min Act: -0.0002

Data Index: 897026 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2378. Min Act: -0.0002

Data Index: 24121 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2377. Min Act: -0.0002

Data Index: 260786 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.1851. Min Act: -0.0002

Data Index: 1153062 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2280. Min Act: -0.0002

Data Index: 280753 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2022. Min Act: -0.0002

Data Index: 941542 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.2216. Min Act: -0.0002

Data Index: 1314800 (C4 (Web Text))

Max Activating Token Index: 7