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

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

Neuron 3542 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.3838. Min Act: -0.0000

Data Index: 382825 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.3603. Min Act: -0.0001

Data Index: 890462 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2990. Min Act: -0.0000

Data Index: 560910 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.3395. Min Act: -0.0001

Data Index: 240266 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2871. Min Act: -0.0000

Data Index: 403932 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.3049. Min Act: -0.0001

Data Index: 907331 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2307. Min Act: -0.0001

Data Index: 248148 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.3514. Min Act: -0.0000

Data Index: 935533 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2988. Min Act: -0.0000

Data Index: 348845 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2944. Min Act: -0.0000

Data Index: 650503 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2455. Min Act: -0.0000

Data Index: 190363 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2700. Min Act: -0.0000

Data Index: 599071 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2531. Min Act: -0.0000

Data Index: 112436 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2418. Min Act: -0.0001

Data Index: 1212517 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2424. Min Act: -0.0000

Data Index: 516466 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2325. Min Act: -0.0000

Data Index: 221738 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.1336. Min Act: -0.0000

Data Index: 556716 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2395. Min Act: -0.0001

Data Index: 426838 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.2047. Min Act: -0.0000

Data Index: 843617 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.1939. Min Act: -0.0000

Data Index: 704883 (C4 (Web Text))

Max Activating Token Index: 473