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

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

Neuron 281 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1114754 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0629. Min Act: -0.0002

Data Index: 71407 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0559. Min Act: -0.0002

Data Index: 633425 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0450. Min Act: -0.0002

Data Index: 813793 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0474. Min Act: -0.0002

Data Index: 208937 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0455. Min Act: -0.0002

Data Index: 876732 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0422. Min Act: -0.0002

Data Index: 109018 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1634115 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0465. Min Act: -0.0002

Data Index: 136861 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0490. Min Act: -0.0002

Data Index: 860462 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0411. Min Act: -0.0002

Data Index: 202682 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0445. Min Act: -0.0002

Data Index: 44858 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1184196 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0460. Min Act: -0.0002

Data Index: 965582 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0458. Min Act: -0.0002

Data Index: 716975 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0439. Min Act: -0.0002

Data Index: 352172 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0436. Min Act: -0.0002

Data Index: 662537 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1260047 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0451. Min Act: -0.0002

Data Index: 724020 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0414. Min Act: -0.0002

Data Index: 571593 (C4 (Web Text))

Max Activating Token Index: 159