Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3289 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0370. Min Range: -4.0370

Max Act: 4.0186. Min Act: -0.0000

Data Index: 420573 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 4.0370. Min Range: -4.0370

Max Act: 4.0370. Min Act: -0.0000

Data Index: 312206 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.6940. Min Act: -0.0000

Data Index: 651789 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.6355. Min Act: -0.0000

Data Index: 1206090 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.6154. Min Act: -0.0000

Data Index: 270799 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.5894. Min Act: -0.0000

Data Index: 515255 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.5486. Min Act: -0.0000

Data Index: 908298 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.4963. Min Act: -0.0000

Data Index: 679646 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.4834. Min Act: -0.0000

Data Index: 797375 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.5075. Min Act: -0.0000

Data Index: 154463 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.3099. Min Act: -0.0000

Data Index: 437059 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.4982. Min Act: -0.0000

Data Index: 1348012 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.3093. Min Act: -0.0000

Data Index: 260787 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.4549. Min Act: -0.0000

Data Index: 329470 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.3947. Min Act: -0.0000

Data Index: 828697 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.3802. Min Act: -0.0000

Data Index: 487563 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.3586. Min Act: -0.0000

Data Index: 1211343 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.2202. Min Act: -0.0000

Data Index: 1034455 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.1839. Min Act: -0.0000

Data Index: 1056731 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 4.0370. Min Range: -4.0370

Max Act: 3.2199. Min Act: -0.0000

Data Index: 411282 (C4 (Web Text))

Max Activating Token Index: 825