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

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

Neuron 2181 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4969. Min Act: -0.0000

Data Index: 70272 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.5007. Min Act: -0.0000

Data Index: 439379 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.5021. Min Act: -0.0000

Data Index: 549613 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1264178 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4642. Min Act: -0.0000

Data Index: 497276 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4705. Min Act: -0.0000

Data Index: 631090 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4862. Min Act: -0.0000

Data Index: 560784 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4883. Min Act: -0.0000

Data Index: 127675 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4491. Min Act: -0.0000

Data Index: 69923 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4230. Min Act: -0.0000

Data Index: 510891 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4257. Min Act: -0.0000

Data Index: 783601 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4397. Min Act: -0.0000

Data Index: 152338 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3987. Min Act: -0.0000

Data Index: 566906 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3866. Min Act: -0.0000

Data Index: 282111 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3952. Min Act: -0.0000

Data Index: 388620 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4040. Min Act: -0.0000

Data Index: 829266 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1077901 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3741. Min Act: -0.0000

Data Index: 824901 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1234077 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3942. Min Act: -0.0000

Data Index: 999584 (C4 (Web Text))

Max Activating Token Index: 957