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

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

Neuron 2869 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: 0.3515. Min Range: -0.3515

Max Act: 0.3466. Min Act: -0.0001

Data Index: 687949 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3329. Min Act: -0.0001

Data Index: 161833 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3515. Min Act: -0.0001

Data Index: 1155709 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3376. Min Act: -0.0001

Data Index: 752003 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3428. Min Act: -0.0001

Data Index: 166808 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3082. Min Act: -0.0001

Data Index: 245050 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3344. Min Act: -0.0001

Data Index: 442836 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3242. Min Act: -0.0001

Data Index: 614083 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3146. Min Act: -0.0001

Data Index: 464091 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2619. Min Act: -0.0001

Data Index: 1303610 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2703. Min Act: -0.0001

Data Index: 72247 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2974. Min Act: -0.0001

Data Index: 1192777 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3098. Min Act: -0.0001

Data Index: 644497 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3067. Min Act: -0.0001

Data Index: 173865 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2980. Min Act: -0.0001

Data Index: 1202636 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2499. Min Act: -0.0001

Data Index: 434880 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2935. Min Act: -0.0001

Data Index: 346263 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3034. Min Act: -0.0001

Data Index: 1269991 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2745. Min Act: -0.0001

Data Index: 1228265 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3116. Min Act: -0.0001

Data Index: 975719 (C4 (Web Text))

Max Activating Token Index: 685