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

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

Neuron 4107 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: 1.3106. Min Range: -1.3106

Max Act: 1.3106. Min Act: -0.0001

Data Index: 415501 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.2496. Min Act: -0.0001

Data Index: 838360 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.1217. Min Act: -0.0001

Data Index: 808909 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.1921. Min Act: -0.0001

Data Index: 1143493 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.1304. Min Act: -0.0001

Data Index: 345418 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.1160. Min Act: -0.0001

Data Index: 356735 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.1059. Min Act: -0.0001

Data Index: 212938 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.1003. Min Act: -0.0001

Data Index: 1089094 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0566. Min Act: -0.0001

Data Index: 915634 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0052. Min Act: -0.0001

Data Index: 1088747 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0599. Min Act: -0.0001

Data Index: 995491 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0814. Min Act: -0.0001

Data Index: 305580 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0414. Min Act: -0.0001

Data Index: 1174851 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0336. Min Act: -0.0001

Data Index: 903342 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0200. Min Act: -0.0001

Data Index: 279783 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0400. Min Act: -0.0001

Data Index: 583179 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0262. Min Act: -0.0001

Data Index: 992068 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0385. Min Act: -0.0001

Data Index: 931596 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0686. Min Act: -0.0001

Data Index: 1027349 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 1.3106. Min Range: -1.3106

Max Act: 0.9902. Min Act: -0.0001

Data Index: 625953 (C4 (Web Text))

Max Activating Token Index: 627