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

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

Neuron 1713 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.8171. Min Act: -0.0000

Data Index: 770676 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.7861. Min Act: -0.0000

Data Index: 643509 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1157921 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.7199. Min Act: -0.0000

Data Index: 768525 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6929. Min Act: -0.0000

Data Index: 725293 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6382. Min Act: -0.0000

Data Index: 975979 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.5510. Min Act: -0.0000

Data Index: 739202 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6142. Min Act: -0.0000

Data Index: 388195 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.5174. Min Act: -0.0000

Data Index: 558351 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1300579 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.4687. Min Act: -0.0000

Data Index: 198323 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.4827. Min Act: -0.0000

Data Index: 601394 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.4662. Min Act: -0.0000

Data Index: 602009 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.4951. Min Act: -0.0000

Data Index: 95967 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.4482. Min Act: -0.0000

Data Index: 78436 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1005479 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1197449 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1333829 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.3989. Min Act: -0.0000

Data Index: 258336 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1235298 (C4 (Web Text))

Max Activating Token Index: 14