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

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

Neuron 1358 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.5433. Min Act: -0.0000

Data Index: 960172 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4744. Min Act: -0.0000

Data Index: 323342 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.5197. Min Act: -0.0000

Data Index: 18579 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4992. Min Act: -0.0001

Data Index: 986737 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1001139 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4883. Min Act: -0.0000

Data Index: 337014 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4330. Min Act: -0.0000

Data Index: 587248 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4377. Min Act: -0.0000

Data Index: 225982 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4526. Min Act: -0.0000

Data Index: 181537 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4240. Min Act: -0.0000

Data Index: 88144 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4665. Min Act: -0.0000

Data Index: 91691 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4337. Min Act: -0.0000

Data Index: 804013 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4503. Min Act: -0.0000

Data Index: 805168 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4478. Min Act: -0.0000

Data Index: 109743 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4450. Min Act: -0.0000

Data Index: 914981 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4599. Min Act: -0.0000

Data Index: 385679 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1197546 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4395. Min Act: -0.0000

Data Index: 990882 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4460. Min Act: -0.0000

Data Index: 144553 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4452. Min Act: -0.0001

Data Index: 772525 (C4 (Web Text))

Max Activating Token Index: 935