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

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

Neuron 903 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.3029. Min Act: -0.0001

Data Index: 263406 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1323573 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2598. Min Act: -0.0001

Data Index: 784794 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2679. Min Act: -0.0001

Data Index: 540843 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2488. Min Act: -0.0000

Data Index: 397892 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2432. Min Act: -0.0001

Data Index: 533486 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2307. Min Act: -0.0000

Data Index: 507636 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2469. Min Act: -0.0000

Data Index: 154301 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2448. Min Act: -0.0000

Data Index: 611284 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2269. Min Act: -0.0000

Data Index: 584818 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2342. Min Act: -0.0000

Data Index: 49615 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2409. Min Act: -0.0000

Data Index: 50009 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2363. Min Act: -0.0001

Data Index: 313355 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2254. Min Act: -0.0000

Data Index: 131071 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2227. Min Act: -0.0001

Data Index: 746551 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2321. Min Act: -0.0001

Data Index: 1149940 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2082. Min Act: -0.0000

Data Index: 274754 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2172. Min Act: -0.0001

Data Index: 353870 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2080. Min Act: -0.0000

Data Index: 569707 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2124. Min Act: -0.0001

Data Index: 533169 (C4 (Web Text))

Max Activating Token Index: 390