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

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

Neuron 975 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7524. Min Range: -4.7524

Max Act: 4.7524. Min Act: -0.0000

Data Index: 316556 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.9351. Min Act: -0.0000

Data Index: 420334 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.8670. Min Act: -0.0000

Data Index: 1103166 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.4847. Min Act: -0.0000

Data Index: 472544 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.6406. Min Act: -0.0000

Data Index: 828925 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.4675. Min Act: -0.0000

Data Index: 57285 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.4595. Min Act: -0.0000

Data Index: 807902 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.5963. Min Act: -0.0000

Data Index: 756783 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.3971. Min Act: -0.0000

Data Index: 85188 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.5242. Min Act: -0.0000

Data Index: 1192808 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.5042. Min Act: -0.0000

Data Index: 845575 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.4801. Min Act: -0.0000

Data Index: 930968 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.4935. Min Act: -0.0000

Data Index: 88265 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.4983. Min Act: -0.0000

Data Index: 1268162 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.5049. Min Act: -0.0000

Data Index: 619314 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.4879. Min Act: -0.0000

Data Index: 185985 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.6508. Min Act: -0.0000

Data Index: 150465 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.6545. Min Act: -0.0000

Data Index: 50260 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.4808. Min Act: -0.0000

Data Index: 859084 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 4.7524. Min Range: -4.7524

Max Act: 3.3253. Min Act: -0.0000

Data Index: 1327433 (C4 (Web Text))

Max Activating Token Index: 540