Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3719 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0874. Min Range: -2.0874

Max Act: 2.0874. Min Act: -0.0000

Data Index: 644622 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.6305. Min Act: -0.0000

Data Index: 1358381 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.3821. Min Act: -0.0000

Data Index: 237204 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.2348. Min Act: -0.0000

Data Index: 718397 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.1652. Min Act: -0.0000

Data Index: 209626 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.1943. Min Act: -0.0000

Data Index: 643051 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1313348 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.0714. Min Act: -0.0000

Data Index: 519631 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.1350. Min Act: -0.0000

Data Index: 312648 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.0547. Min Act: -0.0000

Data Index: 133726 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.1366. Min Act: -0.0000

Data Index: 922084 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.0472. Min Act: -0.0000

Data Index: 443938 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.0994. Min Act: -0.0000

Data Index: 1260820 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.1009. Min Act: -0.0000

Data Index: 689675 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 2.0874. Min Range: -2.0874

Max Act: 0.9671. Min Act: -0.0000

Data Index: 754303 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.0267. Min Act: -0.0000

Data Index: 532322 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.0211. Min Act: -0.0000

Data Index: 857598 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.0124. Min Act: -0.0000

Data Index: 956719 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 2.0874. Min Range: -2.0874

Max Act: 1.0154. Min Act: -0.0000

Data Index: 937973 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 2.0874. Min Range: -2.0874

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1357434 (C4 (Web Text))

Max Activating Token Index: 482