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

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

Neuron 322 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0001

Data Index: 465999 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0325. Min Act: -0.0001

Data Index: 818881 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0322. Min Act: -0.0001

Data Index: 742753 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0305. Min Act: -0.0001

Data Index: 204291 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0276. Min Act: -0.0001

Data Index: 255500 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0310. Min Act: -0.0001

Data Index: 104878 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1174496 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1228163 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0275. Min Act: -0.0001

Data Index: 560219 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1246838 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0263. Min Act: -0.0001

Data Index: 237392 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0262. Min Act: -0.0001

Data Index: 36977 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1002781 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0258. Min Act: -0.0001

Data Index: 194648 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0273. Min Act: -0.0001

Data Index: 1206535 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0216. Min Act: -0.0001

Data Index: 354959 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1260091 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1210132 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0257. Min Act: -0.0001

Data Index: 37779 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1172885 (C4 (Web Text))

Max Activating Token Index: 283