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

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

Neuron 357 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1319734 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.9253. Min Act: -0.0000

Data Index: 195762 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1235460 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1121596 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1147139 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8557. Min Act: -0.0000

Data Index: 615267 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1281280 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1350837 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1220720 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1275208 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1030694 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1349392 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7547. Min Act: -0.0000

Data Index: 690233 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7414. Min Act: -0.0000

Data Index: 848226 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.6974. Min Act: -0.0000

Data Index: 351876 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7316. Min Act: -0.0000

Data Index: 262305 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7342. Min Act: -0.0000

Data Index: 386530 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7284. Min Act: -0.0000

Data Index: 295080 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7329. Min Act: -0.0000

Data Index: 569440 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7659. Min Act: -0.0000

Data Index: 163640 (C4 (Web Text))

Max Activating Token Index: 933