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

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

Neuron 4415 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2156. Min Range: -1.2156

Max Act: 1.2156. Min Act: -0.0000

Data Index: 48730 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.2156. Min Range: -1.2156

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1462123 (Python Code)

Max Activating Token Index: 958

Text #2

Max Range: 1.2156. Min Range: -1.2156

Max Act: 1.0682. Min Act: -0.0000

Data Index: 504536 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.2156. Min Range: -1.2156

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1596523 (Python Code)

Max Activating Token Index: 839

Text #4

Max Range: 1.2156. Min Range: -1.2156

Max Act: 1.0859. Min Act: -0.0000

Data Index: 429268 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 1.2156. Min Range: -1.2156

Max Act: 1.0664. Min Act: -0.0000

Data Index: 924879 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9568. Min Act: -0.0000

Data Index: 746991 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8970. Min Act: 0.0000

Data Index: 263980 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1632867 (Python Code)

Max Activating Token Index: 733

Text #9

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9022. Min Act: -0.0000

Data Index: 984046 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9198. Min Act: -0.0000

Data Index: 469398 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1065208 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.9028. Min Act: -0.0000

Data Index: 703798 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.7829. Min Act: -0.0000

Data Index: 929641 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8806. Min Act: -0.0000

Data Index: 137617 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8044. Min Act: -0.0000

Data Index: 336240 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1553530 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1069351 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.7208. Min Act: -0.0000

Data Index: 224834 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 1.2156. Min Range: -1.2156

Max Act: 0.8032. Min Act: -0.0000

Data Index: 184125 (C4 (Web Text))

Max Activating Token Index: 722