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

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

Neuron 4734 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3454. Min Act: -0.0000

Data Index: 318629 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3213. Min Act: -0.0000

Data Index: 36772 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1041983 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1362498 (Python Code)

Max Activating Token Index: 466

Text #4

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2958. Min Act: -0.0000

Data Index: 369568 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2939. Min Act: -0.0000

Data Index: 9370 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2662. Min Act: -0.0000

Data Index: 66990 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2655. Min Act: -0.0000

Data Index: 431514 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2278. Min Act: -0.0000

Data Index: 168306 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1491975 (Python Code)

Max Activating Token Index: 1022

Text #10

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2320. Min Act: -0.0000

Data Index: 853110 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2224. Min Act: -0.0000

Data Index: 567106 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1085694 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2194. Min Act: -0.0000

Data Index: 829234 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2222. Min Act: -0.0000

Data Index: 166164 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2095. Min Act: -0.0000

Data Index: 96237 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1114732 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2135. Min Act: -0.0000

Data Index: 836287 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2298. Min Act: -0.0000

Data Index: 708041 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.3454. Min Range: -0.3454

Max Act: 0.2220. Min Act: 0.0000

Data Index: 1378774 (Python Code)

Max Activating Token Index: 694