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

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

Neuron 534 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1243078 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1018729 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1223654 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.3218. Min Act: -0.0000

Data Index: 157407 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1087439 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2935. Min Act: -0.0000

Data Index: 359634 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2935. Min Act: -0.0000

Data Index: 478268 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2867. Min Act: -0.0000

Data Index: 416278 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2835. Min Act: -0.0000

Data Index: 984260 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2820. Min Act: -0.0000

Data Index: 285114 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2810. Min Act: -0.0000

Data Index: 278755 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2796. Min Act: -0.0000

Data Index: 757684 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2585. Min Act: -0.0000

Data Index: 348422 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2857. Min Act: -0.0000

Data Index: 642601 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2539. Min Act: -0.0000

Data Index: 476856 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2696. Min Act: -0.0000

Data Index: 720331 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2629. Min Act: -0.0000

Data Index: 602238 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1355440 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2698. Min Act: -0.0000

Data Index: 198092 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.3228. Min Range: -0.3228

Max Act: 0.2598. Min Act: -0.0000

Data Index: 867353 (C4 (Web Text))

Max Activating Token Index: 762