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

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

Neuron 421 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.7106. Min Act: -0.0001

Data Index: 577530 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.5892. Min Act: -0.0001

Data Index: 885259 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.6796. Min Act: -0.0001

Data Index: 114280 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.5588. Min Act: -0.0001

Data Index: 1165195 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.5020. Min Act: -0.0001

Data Index: 691631 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.4888. Min Act: -0.0001

Data Index: 597199 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.4921. Min Act: -0.0001

Data Index: 291393 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.4931. Min Act: -0.0001

Data Index: 873313 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.4357. Min Act: -0.0001

Data Index: 238138 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.4100. Min Act: -0.0001

Data Index: 549546 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.2966. Min Act: -0.0001

Data Index: 80544 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3658. Min Act: -0.0001

Data Index: 1255762 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3287. Min Act: -0.0001

Data Index: 906256 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.4624. Min Act: -0.0001

Data Index: 15976 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3213. Min Act: -0.0001

Data Index: 439522 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.2479. Min Act: -0.0001

Data Index: 777630 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3210. Min Act: -0.0001

Data Index: 643512 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.2629. Min Act: -0.0001

Data Index: 125479 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3041. Min Act: -0.0001

Data Index: 1146328 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.2568. Min Act: -0.0001

Data Index: 1290586 (C4 (Web Text))

Max Activating Token Index: 470