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

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

Neuron 3241 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.3599. Min Act: -0.0000

Data Index: 737035 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.3139. Min Act: -0.0000

Data Index: 550848 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2882. Min Act: -0.0000

Data Index: 796100 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2719. Min Act: -0.0000

Data Index: 826809 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2640. Min Act: -0.0001

Data Index: 697351 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2680. Min Act: -0.0001

Data Index: 429629 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1341246 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2750. Min Act: -0.0000

Data Index: 965065 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2519. Min Act: -0.0000

Data Index: 195375 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2496. Min Act: -0.0000

Data Index: 922770 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2362. Min Act: -0.0001

Data Index: 7754 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2303. Min Act: -0.0001

Data Index: 793750 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2432. Min Act: -0.0000

Data Index: 67854 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2286. Min Act: -0.0001

Data Index: 706345 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2500. Min Act: -0.0001

Data Index: 1118108 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1111990 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2279. Min Act: -0.0001

Data Index: 987583 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2454. Min Act: -0.0001

Data Index: 380430 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1248279 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2158. Min Act: -0.0000

Data Index: 938580 (C4 (Web Text))

Max Activating Token Index: 600