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

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

Neuron 341 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.2735. Min Act: -0.0000

Data Index: 187466 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0875. Min Act: -0.0000

Data Index: 825963 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.8102. Min Act: -0.0001

Data Index: 1358026 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1622. Min Act: -0.0001

Data Index: 993621 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.2498. Min Act: -0.0000

Data Index: 317155 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0341. Min Act: -0.0000

Data Index: 820199 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0311. Min Act: -0.0001

Data Index: 892235 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.8396. Min Act: -0.0001

Data Index: 696284 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.9353. Min Act: -0.0001

Data Index: 362802 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.9282. Min Act: -0.0001

Data Index: 1218898 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.8336. Min Act: -0.0001

Data Index: 414552 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.9654. Min Act: -0.0001

Data Index: 733029 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.7633. Min Act: -0.0000

Data Index: 1094057 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.6820. Min Act: -0.0000

Data Index: 685291 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.7405. Min Act: -0.0001

Data Index: 1256510 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.9481. Min Act: -0.0001

Data Index: 931467 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.7495. Min Act: -0.0000

Data Index: 1260023 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.7651. Min Act: -0.0001

Data Index: 1088051 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.6803. Min Act: -0.0000

Data Index: 49201 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 3.2735. Min Range: -3.2735

Max Act: 2.8778. Min Act: -0.0001

Data Index: 676528 (C4 (Web Text))

Max Activating Token Index: 883