Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 637 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0270. Min Act: -0.0006

Data Index: 796730 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0245. Min Act: -0.0006

Data Index: 370065 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0238. Min Act: -0.0006

Data Index: 898098 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0240. Min Act: -0.0006

Data Index: 670471 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0218. Min Act: -0.0006

Data Index: 311685 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1254260 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1041284 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0217. Min Act: -0.0006

Data Index: 917845 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1034378 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0214. Min Act: -0.0006

Data Index: 228850 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0208. Min Act: -0.0006

Data Index: 882638 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1306232 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0206. Min Act: -0.0006

Data Index: 754519 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0204. Min Act: -0.0006

Data Index: 890743 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0208. Min Act: -0.0006

Data Index: 292566 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0204. Min Act: -0.0006

Data Index: 983145 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0204. Min Act: -0.0006

Data Index: 737817 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0203. Min Act: -0.0006

Data Index: 259382 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0203. Min Act: -0.0006

Data Index: 971562 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1134420 (C4 (Web Text))

Max Activating Token Index: 98