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

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

Neuron 3276 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0001

Data Index: 91516 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0664. Min Act: -0.0001

Data Index: 342348 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1356815 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0535. Min Act: -0.0001

Data Index: 925460 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0526. Min Act: -0.0001

Data Index: 266357 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0531. Min Act: -0.0001

Data Index: 245862 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0547. Min Act: -0.0001

Data Index: 187367 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0507. Min Act: -0.0001

Data Index: 856393 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0490. Min Act: -0.0001

Data Index: 741767 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0505. Min Act: -0.0001

Data Index: 405201 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0518. Min Act: -0.0001

Data Index: 813480 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0514. Min Act: -0.0001

Data Index: 958218 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0526. Min Act: -0.0001

Data Index: 862847 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0523. Min Act: -0.0001

Data Index: 626758 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1091072 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0467. Min Act: -0.0000

Data Index: 577766 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0499. Min Act: -0.0001

Data Index: 800735 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0498. Min Act: -0.0001

Data Index: 60843 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0498. Min Act: -0.0001

Data Index: 961905 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0480. Min Act: -0.0001

Data Index: 672314 (C4 (Web Text))

Max Activating Token Index: 740