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

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

Neuron 1585 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.2215. Min Act: -0.0000

Data Index: 878228 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1291397 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1269820 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.9530. Min Act: -0.0000

Data Index: 443898 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.9352. Min Act: -0.0000

Data Index: 798802 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.9701. Min Act: -0.0000

Data Index: 260046 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1270779 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.8665. Min Act: -0.0000

Data Index: 580480 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.8608. Min Act: -0.0000

Data Index: 334735 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.8425. Min Act: -0.0000

Data Index: 348536 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.8077. Min Act: -0.0000

Data Index: 8909 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.8093. Min Act: -0.0000

Data Index: 49838 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1132871 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.7349. Min Act: -0.0000

Data Index: 79151 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.7936. Min Act: -0.0000

Data Index: 810040 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1178713 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.7538. Min Act: -0.0000

Data Index: 741670 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.7483. Min Act: -0.0000

Data Index: 447669 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1114896 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 1.2215. Min Range: -1.2215

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1279010 (C4 (Web Text))

Max Activating Token Index: 782