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

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

Neuron 3173 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6054. Min Act: -0.0000

Data Index: 157336 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6702. Min Act: -0.0000

Data Index: 366952 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1259815 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1334127 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4356. Min Act: -0.0000

Data Index: 55184 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4028. Min Act: -0.0000

Data Index: 119067 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4581. Min Act: -0.0000

Data Index: 105220 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4549. Min Act: -0.0000

Data Index: 533932 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4261. Min Act: -0.0000

Data Index: 705620 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4157. Min Act: -0.0000

Data Index: 364290 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4611. Min Act: -0.0000

Data Index: 880685 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4340. Min Act: -0.0000

Data Index: 562225 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.3933. Min Act: -0.0000

Data Index: 447277 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4635. Min Act: -0.0000

Data Index: 552916 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4182. Min Act: -0.0000

Data Index: 549416 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4099. Min Act: -0.0000

Data Index: 648095 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1307594 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.3625. Min Act: -0.0000

Data Index: 345507 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4054. Min Act: -0.0000

Data Index: 57002 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4055. Min Act: -0.0000

Data Index: 445338 (C4 (Web Text))

Max Activating Token Index: 75