Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5995 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2944. Min Act: -0.0002

Data Index: 645688 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2576. Min Act: -0.0002

Data Index: 492645 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2398. Min Act: -0.0002

Data Index: 889732 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2567. Min Act: -0.0002

Data Index: 259492 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2559. Min Act: -0.0002

Data Index: 115447 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2628. Min Act: -0.0002

Data Index: 614229 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2484. Min Act: -0.0002

Data Index: 604689 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2387. Min Act: -0.0002

Data Index: 737376 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2522. Min Act: -0.0002

Data Index: 468806 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2544. Min Act: -0.0002

Data Index: 377326 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2408. Min Act: -0.0002

Data Index: 112378 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2273. Min Act: -0.0002

Data Index: 294688 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2326. Min Act: -0.0002

Data Index: 327390 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2324. Min Act: -0.0002

Data Index: 104363 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2328. Min Act: -0.0002

Data Index: 738330 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2382. Min Act: -0.0002

Data Index: 897018 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2303. Min Act: -0.0002

Data Index: 1293069 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2455. Min Act: -0.0002

Data Index: 893303 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2287. Min Act: -0.0002

Data Index: 477517 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2293. Min Act: -0.0002

Data Index: 613678 (C4 (Web Text))

Max Activating Token Index: 509