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

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

Neuron 2429 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.6100. Min Act: -0.0001

Data Index: 768419 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.6870. Min Act: -0.0000

Data Index: 880427 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.4110. Min Act: -0.0001

Data Index: 1052445 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.4112. Min Act: -0.0000

Data Index: 926897 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.5405. Min Act: -0.0001

Data Index: 70652 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.4312. Min Act: -0.0001

Data Index: 939951 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.7275. Min Act: -0.0001

Data Index: 476166 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.4985. Min Act: -0.0000

Data Index: 1277267 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.5727. Min Act: -0.0001

Data Index: 453025 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.2933. Min Act: -0.0001

Data Index: 778857 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.3304. Min Act: -0.0000

Data Index: 943930 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.4250. Min Act: -0.0001

Data Index: 1061685 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.4252. Min Act: -0.0001

Data Index: 1075070 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.3190. Min Act: -0.0001

Data Index: 126678 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.2683. Min Act: -0.0001

Data Index: 1222386 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.5743. Min Act: -0.0000

Data Index: 480543 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.3350. Min Act: -0.0000

Data Index: 885487 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.2356. Min Act: -0.0001

Data Index: 1116227 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.2711. Min Act: -0.0001

Data Index: 822763 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.2004. Min Act: -0.0001

Data Index: 529868 (C4 (Web Text))

Max Activating Token Index: 498