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

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

Neuron 1338 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.4401. Min Act: -0.0000

Data Index: 416743 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.4519. Min Act: -0.0000

Data Index: 718120 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.4234. Min Act: -0.0000

Data Index: 154044 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.4221. Min Act: -0.0000

Data Index: 358722 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.4004. Min Act: -0.0000

Data Index: 589204 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3897. Min Act: -0.0001

Data Index: 1511799 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3863. Min Act: 0.0000

Data Index: 929429 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3555. Min Act: -0.0000

Data Index: 13545 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1020662 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1359478 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1163170 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1451121 (Python Code)

Max Activating Token Index: 523

Text #12

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3560. Min Act: -0.0000

Data Index: 520554 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3574. Min Act: -0.0000

Data Index: 758762 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1216709 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3496. Min Act: -0.0000

Data Index: 729365 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3433. Min Act: -0.0000

Data Index: 263131 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3273. Min Act: -0.0000

Data Index: 419853 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1320415 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3195. Min Act: -0.0000

Data Index: 897149 (C4 (Web Text))

Max Activating Token Index: 217