Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 998 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.6436. Min Act: -0.0001

Data Index: 39067 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.7445. Min Act: -0.0001

Data Index: 613872 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.3569. Min Act: -0.0001

Data Index: 1283540 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.4161. Min Act: -0.0001

Data Index: 402264 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.2500. Min Act: -0.0001

Data Index: 71891 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.3595. Min Act: -0.0001

Data Index: 72150 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.4865. Min Act: -0.0001

Data Index: 1221015 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.3269. Min Act: -0.0001

Data Index: 800372 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.1252. Min Act: -0.0001

Data Index: 533240 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.1876. Min Act: -0.0001

Data Index: 830445 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.0758. Min Act: -0.0001

Data Index: 1241909 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.1321. Min Act: -0.0001

Data Index: 999253 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.1465. Min Act: -0.0001

Data Index: 464795 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.0968. Min Act: -0.0001

Data Index: 668302 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.0726. Min Act: -0.0001

Data Index: 1038533 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.1392. Min Act: -0.0001

Data Index: 67573 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.0741. Min Act: -0.0001

Data Index: 1299204 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.1571. Min Act: -0.0001

Data Index: 652666 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.0384. Min Act: -0.0001

Data Index: 1324993 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 1.7445. Min Range: -1.7445

Max Act: 1.0877. Min Act: -0.0001

Data Index: 295138 (C4 (Web Text))

Max Activating Token Index: 882