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

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

Neuron 258 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4715. Min Act: -0.0002

Data Index: 1049370 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4465. Min Act: -0.0002

Data Index: 548208 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4681. Min Act: -0.0002

Data Index: 72292 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4292. Min Act: -0.0002

Data Index: 70430 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4185. Min Act: -0.0002

Data Index: 182644 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4308. Min Act: -0.0002

Data Index: 1223800 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4154. Min Act: -0.0002

Data Index: 1274673 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4111. Min Act: -0.0002

Data Index: 699988 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4159. Min Act: -0.0002

Data Index: 87996 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4127. Min Act: -0.0002

Data Index: 1021221 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4252. Min Act: -0.0002

Data Index: 692964 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4120. Min Act: -0.0002

Data Index: 287201 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4230. Min Act: -0.0002

Data Index: 1219664 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4163. Min Act: -0.0002

Data Index: 1341085 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4033. Min Act: -0.0002

Data Index: 1167921 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4025. Min Act: -0.0002

Data Index: 820839 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3999. Min Act: -0.0002

Data Index: 32051 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3879. Min Act: -0.0002

Data Index: 464563 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3905. Min Act: -0.0002

Data Index: 510814 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3901. Min Act: -0.0002

Data Index: 602228 (C4 (Web Text))

Max Activating Token Index: 76