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

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

Neuron 2957 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: 1.3772. Min Range: -1.3772

Max Act: 1.3421. Min Act: -0.0001

Data Index: 757797 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.3772. Min Act: -0.0001

Data Index: 951160 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.2300. Min Act: -0.0001

Data Index: 283015 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.2269. Min Act: -0.0001

Data Index: 163229 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.2193. Min Act: -0.0001

Data Index: 534332 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1842. Min Act: -0.0001

Data Index: 253500 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1111. Min Act: -0.0001

Data Index: 336249 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1394. Min Act: -0.0001

Data Index: 1118189 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1396. Min Act: -0.0000

Data Index: 179581 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1445. Min Act: -0.0001

Data Index: 134784 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1138. Min Act: -0.0001

Data Index: 258880 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.0847. Min Act: -0.0001

Data Index: 1022658 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1240. Min Act: -0.0000

Data Index: 734676 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1158. Min Act: -0.0001

Data Index: 1281266 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1096. Min Act: -0.0001

Data Index: 171732 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1090. Min Act: -0.0001

Data Index: 1344550 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1005. Min Act: -0.0000

Data Index: 554344 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1386. Min Act: -0.0001

Data Index: 959544 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1092. Min Act: -0.0001

Data Index: 556610 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 1.3772. Min Range: -1.3772

Max Act: 1.1317. Min Act: -0.0001

Data Index: 763668 (C4 (Web Text))

Max Activating Token Index: 272