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

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

Neuron 1815 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2936. Min Act: -0.0001

Data Index: 1304972 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2536. Min Act: -0.0001

Data Index: 712760 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1068307 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2152. Min Act: -0.0001

Data Index: 365829 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2329. Min Act: -0.0001

Data Index: 858794 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1191797 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1092641 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1010858 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2127. Min Act: -0.0001

Data Index: 834819 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2180. Min Act: -0.0001

Data Index: 63319 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2194. Min Act: -0.0001

Data Index: 9634 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2281. Min Act: -0.0001

Data Index: 891791 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2180. Min Act: -0.0001

Data Index: 452139 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2241. Min Act: -0.0000

Data Index: 546979 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2064. Min Act: -0.0001

Data Index: 371851 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2296. Min Act: -0.0001

Data Index: 987349 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2262. Min Act: -0.0001

Data Index: 1313606 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2142. Min Act: -0.0001

Data Index: 945756 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2077. Min Act: -0.0001

Data Index: 1354427 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1998. Min Act: -0.0000

Data Index: 264762 (C4 (Web Text))

Max Activating Token Index: 594