Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 834 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2685. Min Act: -0.0003

Data Index: 629237 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2784. Min Act: -0.0003

Data Index: 1302094 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2475. Min Act: -0.0003

Data Index: 473607 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2581. Min Act: -0.0003

Data Index: 1272746 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2551. Min Act: -0.0003

Data Index: 404608 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2569. Min Act: -0.0003

Data Index: 712277 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2494. Min Act: -0.0003

Data Index: 1359361 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2567. Min Act: -0.0003

Data Index: 1109530 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2555. Min Act: -0.0003

Data Index: 854913 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2374. Min Act: -0.0003

Data Index: 1221891 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2384. Min Act: -0.0003

Data Index: 26640 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2521. Min Act: -0.0003

Data Index: 755086 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2331. Min Act: -0.0003

Data Index: 312744 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2247. Min Act: -0.0003

Data Index: 88750 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2317. Min Act: -0.0004

Data Index: 216358 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2305. Min Act: -0.0003

Data Index: 332522 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2290. Min Act: -0.0003

Data Index: 347623 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2340. Min Act: -0.0003

Data Index: 916376 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2264. Min Act: -0.0003

Data Index: 804721 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2284. Min Act: -0.0003

Data Index: 483031 (C4 (Web Text))

Max Activating Token Index: 567