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

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

Neuron 1770 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3674. Min Act: 0.0000

Data Index: 457613 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3401. Min Act: -0.0000

Data Index: 302496 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3601. Min Act: -0.0000

Data Index: 13490 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3396. Min Act: -0.0000

Data Index: 428199 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3265. Min Act: -0.0000

Data Index: 138283 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3342. Min Act: -0.0000

Data Index: 135778 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3071. Min Act: -0.0000

Data Index: 229806 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3052. Min Act: -0.0000

Data Index: 474256 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3164. Min Act: -0.0000

Data Index: 899624 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3024. Min Act: -0.0000

Data Index: 34055 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3344. Min Act: -0.0000

Data Index: 93764 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1000594 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3335. Min Act: -0.0000

Data Index: 931979 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2982. Min Act: 0.0000

Data Index: 846018 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1237904 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3059. Min Act: -0.0000

Data Index: 674790 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2909. Min Act: -0.0000

Data Index: 671797 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2983. Min Act: -0.0000

Data Index: 170726 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1192600 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3171. Min Act: 0.0000

Data Index: 819709 (C4 (Web Text))

Max Activating Token Index: 806