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

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

Neuron 1050 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3147. Min Range: -2.3147

Max Act: 2.3147. Min Act: -0.0000

Data Index: 950329 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 2.3147. Min Range: -2.3147

Max Act: 2.2532. Min Act: -0.0000

Data Index: 535926 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 2.3147. Min Range: -2.3147

Max Act: 2.2429. Min Act: -0.0000

Data Index: 145550 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 2.3147. Min Range: -2.3147

Max Act: 2.0728. Min Act: -0.0000

Data Index: 1198274 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.9110. Min Act: -0.0000

Data Index: 1249038 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.7576. Min Act: -0.0000

Data Index: 1117857 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.6590. Min Act: -0.0000

Data Index: 401851 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.9079. Min Act: -0.0000

Data Index: 833393 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.6755. Min Act: -0.0000

Data Index: 518846 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.7376. Min Act: -0.0000

Data Index: 519882 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.7128. Min Act: -0.0000

Data Index: 714042 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.6644. Min Act: -0.0000

Data Index: 876590 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.5852. Min Act: -0.0000

Data Index: 420061 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.4633. Min Act: -0.0000

Data Index: 302562 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.2866. Min Act: -0.0000

Data Index: 492132 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.4782. Min Act: -0.0000

Data Index: 333279 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.2567. Min Act: -0.0000

Data Index: 269512 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.3476. Min Act: 0.0001

Data Index: 1646182 (Python Code)

Max Activating Token Index: 786

Text #18

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.2260. Min Act: -0.0000

Data Index: 191866 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 2.3147. Min Range: -2.3147

Max Act: 1.3313. Min Act: -0.0000

Data Index: 504433 (C4 (Web Text))

Max Activating Token Index: 408