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

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

Neuron 5762 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1541. Min Range: -1.1541

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1358477 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.1541. Min Range: -1.1541

Max Act: 1.1367. Min Act: -0.0000

Data Index: 502669 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1064393 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.9550. Min Act: -0.0000

Data Index: 1013188 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.9855. Min Act: -0.0000

Data Index: 643601 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.9872. Min Act: -0.0000

Data Index: 331530 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.8946. Min Act: -0.0000

Data Index: 299759 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.9099. Min Act: -0.0000

Data Index: 853263 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.9054. Min Act: -0.0000

Data Index: 970005 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.9087. Min Act: -0.0000

Data Index: 175897 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1207319 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.8458. Min Act: -0.0000

Data Index: 498561 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.8363. Min Act: -0.0000

Data Index: 1137822 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.8115. Min Act: -0.0000

Data Index: 171140 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1215514 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.8862. Min Act: -0.0000

Data Index: 947177 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.8774. Min Act: -0.0000

Data Index: 198972 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.8793. Min Act: -0.0000

Data Index: 775037 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.8591. Min Act: -0.0000

Data Index: 72743 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1035049 (C4 (Web Text))

Max Activating Token Index: 1003