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

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

Neuron 1639 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0482. Min Act: -0.0001

Data Index: 899509 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0481. Min Act: -0.0001

Data Index: 750862 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0442. Min Act: -0.0002

Data Index: 716428 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1227697 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1059046 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0444. Min Act: -0.0002

Data Index: 408279 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0451. Min Act: -0.0001

Data Index: 932314 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1161208 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0426. Min Act: -0.0002

Data Index: 580133 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0455. Min Act: -0.0001

Data Index: 847456 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0426. Min Act: -0.0002

Data Index: 644256 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0374. Min Act: -0.0001

Data Index: 341315 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0420. Min Act: -0.0002

Data Index: 384404 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0430. Min Act: -0.0001

Data Index: 132845 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0416. Min Act: -0.0001

Data Index: 246018 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0431. Min Act: -0.0001

Data Index: 412504 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0433. Min Act: -0.0001

Data Index: 524905 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0399. Min Act: -0.0001

Data Index: 250625 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0437. Min Act: -0.0002

Data Index: 612026 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0401. Min Act: -0.0001

Data Index: 789375 (C4 (Web Text))

Max Activating Token Index: 1004