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

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

Neuron 1497 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5791. Min Act: -0.0000

Data Index: 774157 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.6053. Min Act: -0.0000

Data Index: 425430 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1258563 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5472. Min Act: -0.0000

Data Index: 483484 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5951. Min Act: -0.0000

Data Index: 632800 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1190481 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5693. Min Act: -0.0000

Data Index: 329628 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1304798 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5344. Min Act: -0.0000

Data Index: 98539 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4966. Min Act: -0.0000

Data Index: 206423 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5133. Min Act: -0.0000

Data Index: 400932 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5433. Min Act: -0.0000

Data Index: 680769 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1142389 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4833. Min Act: -0.0000

Data Index: 258783 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1317420 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4733. Min Act: -0.0000

Data Index: 204912 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1136210 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4777. Min Act: -0.0000

Data Index: 696488 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4827. Min Act: -0.0000

Data Index: 372257 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4559. Min Act: -0.0000

Data Index: 245602 (C4 (Web Text))

Max Activating Token Index: 281