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

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

Neuron 3056 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.9966. Min Act: -0.0001

Data Index: 1261000 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.9050. Min Act: -0.0001

Data Index: 791955 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.8976. Min Act: -0.0001

Data Index: 34265 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.8933. Min Act: -0.0001

Data Index: 203474 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.8439. Min Act: -0.0001

Data Index: 1124144 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.8332. Min Act: -0.0001

Data Index: 833724 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.8329. Min Act: -0.0001

Data Index: 1392094 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7904. Min Act: -0.0001

Data Index: 736631 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.8222. Min Act: -0.0001

Data Index: 101564 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7835. Min Act: -0.0001

Data Index: 1094348 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7781. Min Act: -0.0001

Data Index: 1167228 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7528. Min Act: -0.0001

Data Index: 57525 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.8008. Min Act: -0.0001

Data Index: 212332 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7411. Min Act: -0.0001

Data Index: 772215 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7350. Min Act: -0.0001

Data Index: 512837 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7556. Min Act: -0.0001

Data Index: 728539 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7318. Min Act: -0.0001

Data Index: 25982 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7522. Min Act: -0.0001

Data Index: 240012 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7541. Min Act: -0.0001

Data Index: 1030285 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7737. Min Act: -0.0001

Data Index: 1131973 (C4 (Web Text))

Max Activating Token Index: 385