Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4085 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.6894. Min Act: -0.0001

Data Index: 379602 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4983. Min Act: -0.0001

Data Index: 118725 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4844. Min Act: -0.0001

Data Index: 826701 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4641. Min Act: -0.0001

Data Index: 1012387 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4485. Min Act: -0.0001

Data Index: 1037681 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4526. Min Act: -0.0001

Data Index: 321593 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4358. Min Act: -0.0001

Data Index: 1332146 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4414. Min Act: -0.0001

Data Index: 1237960 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4601. Min Act: -0.0001

Data Index: 119162 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4694. Min Act: -0.0001

Data Index: 705960 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4259. Min Act: -0.0001

Data Index: 1345769 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4074. Min Act: -0.0001

Data Index: 860027 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.3913. Min Act: -0.0001

Data Index: 446199 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4153. Min Act: -0.0001

Data Index: 437747 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4102. Min Act: -0.0001

Data Index: 1298374 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.3935. Min Act: -0.0001

Data Index: 54466 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4185. Min Act: -0.0001

Data Index: 497772 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.3766. Min Act: -0.0001

Data Index: 19663 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4241. Min Act: -0.0001

Data Index: 672883 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.3771. Min Act: -0.0001

Data Index: 700814 (C4 (Web Text))

Max Activating Token Index: 433