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

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

Neuron 1918 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5085. Min Act: -0.0003

Data Index: 1151157 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4474. Min Act: -0.0003

Data Index: 1074925 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4470. Min Act: -0.0003

Data Index: 1128025 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5098. Min Act: -0.0003

Data Index: 941330 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5780. Min Act: -0.0003

Data Index: 416135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5023. Min Act: -0.0003

Data Index: 949919 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4614. Min Act: -0.0003

Data Index: 670800 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5470. Min Act: -0.0003

Data Index: 17461 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4093. Min Act: -0.0003

Data Index: 1001527 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4855. Min Act: -0.0003

Data Index: 57643 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4504. Min Act: -0.0004

Data Index: 282298 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4209. Min Act: -0.0004

Data Index: 585714 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4165. Min Act: -0.0003

Data Index: 725927 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3632. Min Act: -0.0004

Data Index: 859037 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5471. Min Act: -0.0003

Data Index: 764962 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4942. Min Act: -0.0003

Data Index: 465412 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4484. Min Act: -0.0003

Data Index: 587637 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5266. Min Act: -0.0003

Data Index: 892274 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3373. Min Act: -0.0003

Data Index: 592109 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5275. Min Act: -0.0003

Data Index: 1116138 (C4 (Web Text))

Max Activating Token Index: 368