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

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

Neuron 1968 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4935. Min Act: -0.0000

Data Index: 479175 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1318281 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3740. Min Act: -0.0000

Data Index: 774236 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3182. Min Act: -0.0000

Data Index: 79644 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3060. Min Act: -0.0000

Data Index: 78752 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3059. Min Act: -0.0000

Data Index: 631308 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1208850 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1282916 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2707. Min Act: -0.0000

Data Index: 434081 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2780. Min Act: -0.0000

Data Index: 727907 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1109488 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2626. Min Act: -0.0000

Data Index: 567606 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1301889 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2608. Min Act: -0.0000

Data Index: 476131 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2612. Min Act: -0.0000

Data Index: 706171 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2480. Min Act: -0.0000

Data Index: 85150 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2610. Min Act: -0.0000

Data Index: 756141 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2493. Min Act: -0.0000

Data Index: 541572 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2609. Min Act: -0.0000

Data Index: 727074 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2443. Min Act: -0.0000

Data Index: 318451 (C4 (Web Text))

Max Activating Token Index: 359