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

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

Neuron 87 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.3564. Min Act: -0.0000

Data Index: 937856 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.3399. Min Act: -0.0001

Data Index: 796824 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.3360. Min Act: -0.0000

Data Index: 720648 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.3186. Min Act: -0.0000

Data Index: 897748 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1049090 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1106408 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2817. Min Act: -0.0000

Data Index: 253388 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2554. Min Act: -0.0000

Data Index: 751730 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1137045 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2669. Min Act: -0.0000

Data Index: 435444 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2508. Min Act: -0.0000

Data Index: 343107 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1326880 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2561. Min Act: -0.0000

Data Index: 533014 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1196354 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2417. Min Act: -0.0000

Data Index: 64038 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2385. Min Act: -0.0000

Data Index: 569945 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2366. Min Act: -0.0000

Data Index: 175203 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2447. Min Act: -0.0000

Data Index: 526083 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2429. Min Act: -0.0000

Data Index: 320608 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2488. Min Act: -0.0000

Data Index: 237658 (C4 (Web Text))

Max Activating Token Index: 999