Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4160 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0481. Min Range: -2.0481

Max Act: 2.0481. Min Act: -0.0000

Data Index: 473175 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.8534. Min Act: -0.0000

Data Index: 1177960 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.9610. Min Act: -0.0000

Data Index: 846429 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.8399. Min Act: -0.0000

Data Index: 54236 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.8039. Min Act: -0.0000

Data Index: 73395 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.7999. Min Act: -0.0000

Data Index: 636609 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.7159. Min Act: -0.0000

Data Index: 797154 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.5849. Min Act: -0.0000

Data Index: 587621 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.6553. Min Act: -0.0000

Data Index: 232509 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.6328. Min Act: -0.0000

Data Index: 52630 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.6220. Min Act: -0.0000

Data Index: 81398 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.5835. Min Act: -0.0000

Data Index: 1153887 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.5486. Min Act: -0.0000

Data Index: 45522 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.5537. Min Act: -0.0000

Data Index: 545622 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1070917 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.5204. Min Act: -0.0000

Data Index: 474950 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.6048. Min Act: -0.0000

Data Index: 1157963 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.4962. Min Act: -0.0000

Data Index: 1166708 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.5727. Min Act: -0.0000

Data Index: 433301 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 2.0481. Min Range: -2.0481

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1119570 (C4 (Web Text))

Max Activating Token Index: 646