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

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

Neuron 1121 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1552324 (Python Code)

Max Activating Token Index: 565

Text #1

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.3186. Min Act: -0.0000

Data Index: 426777 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.3062. Min Act: -0.0000

Data Index: 13439 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.3018. Min Act: 0.0000

Data Index: 1636050 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.3063. Min Act: -0.0000

Data Index: 89447 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2838. Min Act: -0.0000

Data Index: 877015 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2840. Min Act: -0.0000

Data Index: 125500 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1047114 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2580. Min Act: 0.0000

Data Index: 380572 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2636. Min Act: 0.0000

Data Index: 612991 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2700. Min Act: -0.0000

Data Index: 314148 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2513. Min Act: -0.0000

Data Index: 741567 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1307396 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1486297 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2398. Min Act: 0.0000

Data Index: 1159335 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2393. Min Act: 0.0000

Data Index: 444725 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2409. Min Act: -0.0000

Data Index: 619986 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2532. Min Act: -0.0000

Data Index: 240461 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2307. Min Act: -0.0000

Data Index: 141177 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1340112 (C4 (Web Text))

Max Activating Token Index: 480