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

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

Neuron 4735 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: 2.0772. Min Range: -2.0772

Max Act: 1.7978. Min Act: -0.0000

Data Index: 448589 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 2.0772. Min Range: -2.0772

Max Act: 2.0772. Min Act: -0.0000

Data Index: 83987 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.5959. Min Act: -0.0000

Data Index: 730825 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.6490. Min Act: -0.0000

Data Index: 29261 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.4553. Min Act: -0.0000

Data Index: 936015 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.6545. Min Act: -0.0000

Data Index: 418112 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.3309. Min Act: -0.0000

Data Index: 983133 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.3065. Min Act: -0.0000

Data Index: 1306674 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.4433. Min Act: -0.0000

Data Index: 586705 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.4330. Min Act: -0.0000

Data Index: 539940 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.5107. Min Act: -0.0000

Data Index: 742289 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.3357. Min Act: -0.0000

Data Index: 503013 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1077433 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1226939 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.2099. Min Act: -0.0000

Data Index: 642773 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1337525 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.1927. Min Act: -0.0000

Data Index: 598447 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.4292. Min Act: -0.0000

Data Index: 1250290 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.2588. Min Act: -0.0000

Data Index: 393931 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 2.0772. Min Range: -2.0772

Max Act: 1.2361. Min Act: -0.0000

Data Index: 694488 (C4 (Web Text))

Max Activating Token Index: 47