Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2152. Min Range: -1.2152

Max Act: 1.2064. Min Act: -0.0001

Data Index: 840762 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 1.2152. Min Range: -1.2152

Max Act: 1.2152. Min Act: -0.0001

Data Index: 1093576 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 1.2152. Min Range: -1.2152

Max Act: 1.0866. Min Act: -0.0001

Data Index: 572045 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 1.2152. Min Range: -1.2152

Max Act: 1.0802. Min Act: -0.0001

Data Index: 148632 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 1.2152. Min Range: -1.2152

Max Act: 1.0465. Min Act: -0.0001

Data Index: 142330 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9924. Min Act: -0.0001

Data Index: 338663 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 1.2152. Min Range: -1.2152

Max Act: 1.0103. Min Act: -0.0001

Data Index: 1240287 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 1.2152. Min Range: -1.2152

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1177318 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9827. Min Act: -0.0001

Data Index: 71668 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9574. Min Act: -0.0001

Data Index: 239254 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9180. Min Act: -0.0001

Data Index: 423805 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9509. Min Act: -0.0001

Data Index: 127747 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9614. Min Act: -0.0001

Data Index: 1026766 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9224. Min Act: -0.0001

Data Index: 710606 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9881. Min Act: -0.0001

Data Index: 86132 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9756. Min Act: -0.0001

Data Index: 1317519 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8487. Min Act: -0.0001

Data Index: 1093164 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8461. Min Act: -0.0000

Data Index: 359851 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.8924. Min Act: -0.0001

Data Index: 816693 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.2152. Min Range: -1.2152

Max Act: 0.9196. Min Act: -0.0001

Data Index: 335635 (C4 (Web Text))

Max Activating Token Index: 266