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

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

Neuron 243 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.4124. Min Act: -0.0000

Data Index: 986283 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1626607 (Python Code)

Max Activating Token Index: 492

Text #2

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1030140 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3259. Min Act: -0.0000

Data Index: 932608 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1225793 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3190. Min Act: -0.0000

Data Index: 472685 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2941. Min Act: -0.0000

Data Index: 601193 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3443. Min Act: -0.0000

Data Index: 895251 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3058. Min Act: -0.0000

Data Index: 97841 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3022. Min Act: -0.0000

Data Index: 523326 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3001. Min Act: -0.0000

Data Index: 692109 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2958. Min Act: -0.0000

Data Index: 783201 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3046. Min Act: -0.0000

Data Index: 718238 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2898. Min Act: -0.0000

Data Index: 275587 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1537810 (Python Code)

Max Activating Token Index: 272

Text #15

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2928. Min Act: -0.0000

Data Index: 599527 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1288489 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2766. Min Act: -0.0000

Data Index: 551749 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1168480 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1074099 (C4 (Web Text))

Max Activating Token Index: 37