Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1606 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0399. Min Range: -1.0399

Max Act: 1.0399. Min Act: -0.0000

Data Index: 75575 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8997. Min Act: -0.0000

Data Index: 259038 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1162161 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9308. Min Act: -0.0000

Data Index: 263606 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1112104 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8587. Min Act: -0.0000

Data Index: 441265 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8277. Min Act: -0.0000

Data Index: 518728 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8302. Min Act: -0.0000

Data Index: 274578 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.6465. Min Act: -0.0000

Data Index: 968634 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7841. Min Act: -0.0000

Data Index: 367681 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1101689 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7065. Min Act: -0.0000

Data Index: 84119 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7916. Min Act: -0.0000

Data Index: 96167 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7813. Min Act: -0.0000

Data Index: 388064 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1183724 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7553. Min Act: -0.0000

Data Index: 912923 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1093467 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7224. Min Act: -0.0000

Data Index: 651420 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7188. Min Act: -0.0001

Data Index: 1259670 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1315133 (C4 (Web Text))

Max Activating Token Index: 368