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

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

Neuron 4718 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: 0.2661. Min Range: -0.2661

Max Act: 0.2661. Min Act: -0.0000

Data Index: 746310 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2459. Min Act: -0.0000

Data Index: 805104 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2395. Min Act: -0.0000

Data Index: 577043 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2379. Min Act: -0.0000

Data Index: 292047 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2378. Min Act: -0.0000

Data Index: 545656 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2420. Min Act: -0.0000

Data Index: 575071 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2237. Min Act: -0.0000

Data Index: 46042 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2207. Min Act: -0.0000

Data Index: 632370 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1156813 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2042. Min Act: -0.0000

Data Index: 536106 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1953. Min Act: -0.0000

Data Index: 560654 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1090633 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2152. Min Act: -0.0000

Data Index: 670004 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2058. Min Act: -0.0000

Data Index: 151125 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1359241 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1027423 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2011. Min Act: -0.0000

Data Index: 648871 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2003. Min Act: -0.0000

Data Index: 859798 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2003. Min Act: -0.0000

Data Index: 158196 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1923. Min Act: -0.0000

Data Index: 997790 (C4 (Web Text))

Max Activating Token Index: 674