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

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

Neuron 2196 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: 1.8490. Min Range: -1.8490

Max Act: 1.7646. Min Act: -0.0001

Data Index: 687055 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.6707. Min Act: -0.0001

Data Index: 1210056 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.7203. Min Act: -0.0001

Data Index: 1155009 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.7635. Min Act: -0.0001

Data Index: 267677 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.5610. Min Act: -0.0001

Data Index: 244259 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.6382. Min Act: -0.0001

Data Index: 1340280 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.6804. Min Act: -0.0001

Data Index: 714813 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.6375. Min Act: -0.0001

Data Index: 684220 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.8490. Min Act: -0.0001

Data Index: 67650 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.6239. Min Act: -0.0001

Data Index: 217140 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.5697. Min Act: -0.0001

Data Index: 1314886 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.4169. Min Act: -0.0001

Data Index: 829958 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.6823. Min Act: -0.0001

Data Index: 1179079 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.6693. Min Act: -0.0001

Data Index: 1173188 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.5985. Min Act: -0.0001

Data Index: 756088 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.5478. Min Act: -0.0001

Data Index: 62231 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.6140. Min Act: -0.0001

Data Index: 552221 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.5646. Min Act: -0.0001

Data Index: 73118 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.4672. Min Act: -0.0001

Data Index: 927339 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.8490. Min Range: -1.8490

Max Act: 1.4663. Min Act: -0.0001

Data Index: 321642 (C4 (Web Text))

Max Activating Token Index: 339