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

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

Neuron 2845 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: 1.4364. Min Range: -1.4364

Max Act: 1.4364. Min Act: -0.0001

Data Index: 731780 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 1.4364. Min Range: -1.4364

Max Act: 1.2969. Min Act: -0.0001

Data Index: 686593 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 1.4364. Min Range: -1.4364

Max Act: 1.2373. Min Act: -0.0001

Data Index: 679877 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 1.4364. Min Range: -1.4364

Max Act: 1.1664. Min Act: -0.0001

Data Index: 1197675 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.4364. Min Range: -1.4364

Max Act: 1.1130. Min Act: -0.0001

Data Index: 675270 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 1.4364. Min Range: -1.4364

Max Act: 1.0508. Min Act: -0.0001

Data Index: 1311902 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.8973. Min Act: -0.0001

Data Index: 168997 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9878. Min Act: -0.0001

Data Index: 1359557 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9466. Min Act: -0.0001

Data Index: 149373 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9927. Min Act: -0.0001

Data Index: 293392 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9909. Min Act: -0.0001

Data Index: 598423 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9323. Min Act: -0.0001

Data Index: 821697 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9560. Min Act: -0.0001

Data Index: 697255 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9426. Min Act: -0.0001

Data Index: 452664 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.8935. Min Act: -0.0001

Data Index: 91478 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9655. Min Act: -0.0001

Data Index: 1261440 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9052. Min Act: -0.0001

Data Index: 119613 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9280. Min Act: -0.0001

Data Index: 390990 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.9334. Min Act: -0.0001

Data Index: 843709 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 1.4364. Min Range: -1.4364

Max Act: 0.8971. Min Act: -0.0001

Data Index: 159317 (C4 (Web Text))

Max Activating Token Index: 149