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

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

Neuron 4945 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.6610. Min Act: -0.0000

Data Index: 385884 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.6127. Min Act: -0.0000

Data Index: 43482 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1026630 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5899. Min Act: -0.0000

Data Index: 265071 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5517. Min Act: -0.0000

Data Index: 911885 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5245. Min Act: -0.0000

Data Index: 681791 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1078290 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4973. Min Act: -0.0000

Data Index: 110676 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4546. Min Act: -0.0000

Data Index: 364490 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1215085 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4217. Min Act: -0.0000

Data Index: 58264 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1006157 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4147. Min Act: -0.0000

Data Index: 724480 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4302. Min Act: -0.0000

Data Index: 452941 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4161. Min Act: -0.0000

Data Index: 600156 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4133. Min Act: -0.0000

Data Index: 969372 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4236. Min Act: -0.0000

Data Index: 763587 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4122. Min Act: -0.0000

Data Index: 26560 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1044924 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1009833 (C4 (Web Text))

Max Activating Token Index: 881