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

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

Neuron 3314 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1759. Min Act: -0.0000

Data Index: 93159 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1796. Min Act: -0.0000

Data Index: 980648 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1169026 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1160135 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1254170 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1499. Min Act: -0.0000

Data Index: 820958 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1267687 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1140869 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1397. Min Act: -0.0001

Data Index: 623974 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1343. Min Act: -0.0001

Data Index: 759354 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1322. Min Act: -0.0001

Data Index: 111025 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1263. Min Act: -0.0000

Data Index: 756922 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1280. Min Act: -0.0001

Data Index: 495050 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1229. Min Act: -0.0001

Data Index: 306141 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1183. Min Act: -0.0001

Data Index: 20663 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1227. Min Act: -0.0000

Data Index: 899180 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1163018 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1069482 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1117. Min Act: -0.0000

Data Index: 900070 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1115. Min Act: -0.0000

Data Index: 674792 (C4 (Web Text))

Max Activating Token Index: 464