Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 971 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: -0.0006

Data Index: 378389 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0484. Min Act: -0.0006

Data Index: 1225289 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0478. Min Act: -0.0006

Data Index: 213372 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0477. Min Act: -0.0006

Data Index: 775824 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0461. Min Act: -0.0005

Data Index: 832102 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0461. Min Act: -0.0006

Data Index: 91610 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0479. Min Act: -0.0006

Data Index: 140054 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0467. Min Act: -0.0006

Data Index: 70715 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0448. Min Act: -0.0006

Data Index: 1121092 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0452. Min Act: -0.0006

Data Index: 235261 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0444. Min Act: -0.0006

Data Index: 29610 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0462. Min Act: -0.0006

Data Index: 1182640 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0450. Min Act: -0.0006

Data Index: 949250 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0470. Min Act: -0.0006

Data Index: 723057 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0451. Min Act: -0.0006

Data Index: 227714 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0442. Min Act: -0.0006

Data Index: 1312461 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0429. Min Act: -0.0006

Data Index: 1225742 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0417. Min Act: -0.0006

Data Index: 372163 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0443. Min Act: -0.0006

Data Index: 682091 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0406. Min Act: -0.0006

Data Index: 386130 (C4 (Web Text))

Max Activating Token Index: 662