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

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

Neuron 2814 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.2752. Min Act: -0.0001

Data Index: 1210979 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.1555. Min Act: -0.0001

Data Index: 1341859 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0253. Min Act: -0.0001

Data Index: 946818 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0818. Min Act: -0.0001

Data Index: 1154681 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0634. Min Act: -0.0001

Data Index: 1315908 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0643. Min Act: -0.0001

Data Index: 194106 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0203. Min Act: -0.0001

Data Index: 72727 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0078. Min Act: -0.0001

Data Index: 1354609 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0200. Min Act: -0.0001

Data Index: 491063 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0460. Min Act: -0.0001

Data Index: 1072136 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0129. Min Act: -0.0001

Data Index: 411897 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9218. Min Act: -0.0001

Data Index: 617536 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9378. Min Act: -0.0001

Data Index: 26575 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9657. Min Act: -0.0001

Data Index: 536640 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.8532. Min Act: -0.0001

Data Index: 908280 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9105. Min Act: -0.0001

Data Index: 899226 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9140. Min Act: -0.0001

Data Index: 1082248 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9674. Min Act: -0.0001

Data Index: 310376 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9325. Min Act: -0.0001

Data Index: 103188 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9666. Min Act: -0.0001

Data Index: 400659 (C4 (Web Text))

Max Activating Token Index: 883