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

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

Neuron 3111 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.2558. Min Act: -0.0000

Data Index: 370680 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.9780. Min Act: -0.0000

Data Index: 408932 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.8923. Min Act: -0.0000

Data Index: 614056 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.6883. Min Act: -0.0000

Data Index: 326441 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.4865. Min Act: -0.0000

Data Index: 90196 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.5083. Min Act: -0.0000

Data Index: 1089209 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.2524. Min Act: -0.0000

Data Index: 278286 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.2369. Min Act: -0.0000

Data Index: 1234170 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.2230. Min Act: -0.0000

Data Index: 368958 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.3506. Min Act: -0.0000

Data Index: 812363 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.1795. Min Act: -0.0000

Data Index: 1220995 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.0691. Min Act: -0.0000

Data Index: 764383 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 4.2558. Min Range: -4.2558

Max Act: 2.8811. Min Act: -0.0000

Data Index: 1405251 (Python Code)

Max Activating Token Index: 517

Text #13

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.0124. Min Act: -0.0000

Data Index: 167388 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.0163. Min Act: -0.0000

Data Index: 133034 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.0859. Min Act: -0.0000

Data Index: 1297394 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.0757. Min Act: -0.0000

Data Index: 387602 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 4.2558. Min Range: -4.2558

Max Act: 2.9442. Min Act: -0.0000

Data Index: 403077 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 4.2558. Min Range: -4.2558

Max Act: 2.8590. Min Act: -0.0000

Data Index: 824686 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 4.2558. Min Range: -4.2558

Max Act: 2.8396. Min Act: -0.0000

Data Index: 276146 (C4 (Web Text))

Max Activating Token Index: 346