Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3052 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.2206. Min Act: -0.0003

Data Index: 110327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.2071. Min Act: -0.0003

Data Index: 179874 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1679. Min Act: -0.0003

Data Index: 492180 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1653. Min Act: -0.0003

Data Index: 363895 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1604. Min Act: -0.0003

Data Index: 231608 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1339. Min Act: -0.0003

Data Index: 592724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1310. Min Act: -0.0003

Data Index: 881879 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1308. Min Act: -0.0003

Data Index: 688422 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1274. Min Act: -0.0003

Data Index: 1312784 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1269. Min Act: -0.0003

Data Index: 773917 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1248. Min Act: -0.0003

Data Index: 1320744 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1234. Min Act: -0.0003

Data Index: 577684 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1232. Min Act: -0.0003

Data Index: 253826 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1170. Min Act: -0.0003

Data Index: 249712 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1210. Min Act: -0.0003

Data Index: 1278519 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1179. Min Act: -0.0003

Data Index: 439591 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1163. Min Act: -0.0003

Data Index: 1237144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1154. Min Act: -0.0003

Data Index: 1346091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1154. Min Act: -0.0003

Data Index: 1237464 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1149. Min Act: -0.0003

Data Index: 1186622 (C4 (Web Text))

Max Activating Token Index: 1023