Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4307 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2816. Min Act: -0.0001

Data Index: 52967 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2877. Min Act: -0.0000

Data Index: 414693 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1085036 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1006429 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2402. Min Act: -0.0000

Data Index: 813461 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2265. Min Act: -0.0000

Data Index: 160116 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2303. Min Act: -0.0000

Data Index: 873261 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1002929 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2528. Min Act: -0.0000

Data Index: 863493 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1001958 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2307. Min Act: -0.0000

Data Index: 95262 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2311. Min Act: -0.0000

Data Index: 276997 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2202. Min Act: -0.0000

Data Index: 794736 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1230635 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2167. Min Act: -0.0000

Data Index: 218322 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1246457 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2108. Min Act: -0.0000

Data Index: 113028 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2174. Min Act: -0.0000

Data Index: 221541 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2071. Min Act: -0.0000

Data Index: 864639 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.2877. Min Range: -0.2877

Max Act: 0.2145. Min Act: -0.0000

Data Index: 8714 (C4 (Web Text))

Max Activating Token Index: 7