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

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

Neuron 2020 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0112. Min Range: -1.0112

Max Act: 1.0112. Min Act: -0.0000

Data Index: 230237 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1275354 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.8472. Min Act: -0.0000

Data Index: 645043 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1115399 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1334724 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.8225. Min Act: -0.0000

Data Index: 290356 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7902. Min Act: -0.0000

Data Index: 854243 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7592. Min Act: -0.0000

Data Index: 862649 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7636. Min Act: -0.0000

Data Index: 988162 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7709. Min Act: -0.0000

Data Index: 603523 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1210108 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7318. Min Act: -0.0000

Data Index: 247424 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6582. Min Act: -0.0000

Data Index: 214155 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7572. Min Act: -0.0000

Data Index: 620484 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1231671 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1004599 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6650. Min Act: -0.0000

Data Index: 690640 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7001. Min Act: -0.0000

Data Index: 432295 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6972. Min Act: -0.0000

Data Index: 844394 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6985. Min Act: -0.0000

Data Index: 692413 (C4 (Web Text))

Max Activating Token Index: 382