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

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

Neuron 1870 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.2792. Min Act: -0.0001

Data Index: 1581869 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0821. Min Act: -0.0001

Data Index: 272195 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0156. Min Act: -0.0002

Data Index: 119837 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0661. Min Act: -0.0001

Data Index: 777085 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0271. Min Act: -0.0001

Data Index: 540442 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0293. Min Act: -0.0001

Data Index: 1304611 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9505. Min Act: -0.0001

Data Index: 138078 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0199. Min Act: -0.0001

Data Index: 257154 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9234. Min Act: -0.0001

Data Index: 1455490 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9927. Min Act: -0.0001

Data Index: 265646 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0404. Min Act: -0.0001

Data Index: 365288 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9510. Min Act: -0.0002

Data Index: 234792 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0023. Min Act: -0.0001

Data Index: 317518 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9373. Min Act: -0.0001

Data Index: 611742 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0545. Min Act: -0.0001

Data Index: 1447712 (Python Code)

Max Activating Token Index: 197

Text #15

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9305. Min Act: -0.0001

Data Index: 1106255 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9656. Min Act: -0.0002

Data Index: 1081745 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9608. Min Act: -0.0002

Data Index: 820560 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9796. Min Act: -0.0001

Data Index: 678889 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.8966. Min Act: -0.0001

Data Index: 811479 (C4 (Web Text))

Max Activating Token Index: 1013