Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 232 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3614. Min Act: -0.0001

Data Index: 868490 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3440. Min Act: -0.0001

Data Index: 85794 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2725. Min Act: -0.0001

Data Index: 262946 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2739. Min Act: -0.0001

Data Index: 596706 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2613. Min Act: -0.0001

Data Index: 426337 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2670. Min Act: -0.0001

Data Index: 624271 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2687. Min Act: -0.0001

Data Index: 962728 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2426. Min Act: -0.0001

Data Index: 179368 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2380. Min Act: -0.0001

Data Index: 665420 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2494. Min Act: -0.0001

Data Index: 685112 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2563. Min Act: -0.0001

Data Index: 580074 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2543. Min Act: -0.0001

Data Index: 1037318 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2551. Min Act: -0.0001

Data Index: 1127057 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2279. Min Act: -0.0001

Data Index: 963650 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2271. Min Act: -0.0001

Data Index: 434059 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2481. Min Act: -0.0001

Data Index: 17474 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2418. Min Act: -0.0001

Data Index: 93746 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2323. Min Act: -0.0001

Data Index: 133291 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2265. Min Act: -0.0001

Data Index: 504419 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2319. Min Act: -0.0001

Data Index: 38340 (C4 (Web Text))

Max Activating Token Index: 894