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

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

Neuron 3217 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7319. Min Range: -3.7319

Max Act: 3.7319. Min Act: -0.0001

Data Index: 750630 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.7319. Min Range: -3.7319

Max Act: 3.6003. Min Act: -0.0001

Data Index: 719271 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 3.7319. Min Range: -3.7319

Max Act: 3.6880. Min Act: -0.0001

Data Index: 1249763 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 3.7319. Min Range: -3.7319

Max Act: 3.3764. Min Act: -0.0001

Data Index: 1314474 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 3.7319. Min Range: -3.7319

Max Act: 3.2436. Min Act: -0.0001

Data Index: 283239 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 3.7319. Min Range: -3.7319

Max Act: 3.0956. Min Act: -0.0001

Data Index: 655940 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 3.7319. Min Range: -3.7319

Max Act: 3.1687. Min Act: -0.0001

Data Index: 174299 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 3.7319. Min Range: -3.7319

Max Act: 2.8670. Min Act: -0.0001

Data Index: 1346909 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 3.7319. Min Range: -3.7319

Max Act: 2.6475. Min Act: -0.0001

Data Index: 506688 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 3.7319. Min Range: -3.7319

Max Act: 2.5691. Min Act: -0.0001

Data Index: 1178795 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 3.7319. Min Range: -3.7319

Max Act: 2.4222. Min Act: -0.0001

Data Index: 1270410 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 3.7319. Min Range: -3.7319

Max Act: 2.3704. Min Act: -0.0001

Data Index: 108297 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 3.7319. Min Range: -3.7319

Max Act: 2.0780. Min Act: -0.0001

Data Index: 1313042 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 3.7319. Min Range: -3.7319

Max Act: 1.9596. Min Act: -0.0001

Data Index: 196056 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 3.7319. Min Range: -3.7319

Max Act: 1.9856. Min Act: -0.0001

Data Index: 257698 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 3.7319. Min Range: -3.7319

Max Act: 1.9832. Min Act: -0.0001

Data Index: 1144167 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 3.7319. Min Range: -3.7319

Max Act: 1.9021. Min Act: -0.0001

Data Index: 982043 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 3.7319. Min Range: -3.7319

Max Act: 1.8442. Min Act: -0.0001

Data Index: 917194 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 3.7319. Min Range: -3.7319

Max Act: 1.9539. Min Act: -0.0001

Data Index: 433855 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 3.7319. Min Range: -3.7319

Max Act: 1.8610. Min Act: -0.0001

Data Index: 639391 (C4 (Web Text))

Max Activating Token Index: 238