Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2067 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.7435. Min Act: -0.0000

Data Index: 904313 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.8003. Min Act: -0.0000

Data Index: 717099 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1606184 (Python Code)

Max Activating Token Index: 562

Text #3

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.4389. Min Act: -0.0000

Data Index: 404140 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.4195. Min Act: -0.0000

Data Index: 57738 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.3522. Min Act: -0.0000

Data Index: 1586099 (Python Code)

Max Activating Token Index: 520

Text #6

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.3796. Min Act: -0.0000

Data Index: 1559175 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.2626. Min Act: -0.0000

Data Index: 710294 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1037297 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.0679. Min Act: -0.0000

Data Index: 114310 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.0608. Min Act: -0.0000

Data Index: 869634 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.0182. Min Act: -0.0000

Data Index: 216391 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 1.8003. Min Range: -1.8003

Max Act: 0.9593. Min Act: -0.0000

Data Index: 336862 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1251953 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 1.8003. Min Range: -1.8003

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1199403 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 1.8003. Min Range: -1.8003

Max Act: 0.9634. Min Act: -0.0000

Data Index: 833709 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.8003. Min Range: -1.8003

Max Act: 0.9803. Min Act: -0.0000

Data Index: 96583 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 1.8003. Min Range: -1.8003

Max Act: 0.7783. Min Act: -0.0000

Data Index: 537314 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 1.8003. Min Range: -1.8003

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1221569 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.8003. Min Range: -1.8003

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1299066 (C4 (Web Text))

Max Activating Token Index: 921