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

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

Neuron 4350 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1056. Min Range: -6.1056

Max Act: 6.1056. Min Act: -0.0000

Data Index: 99580 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 6.1056. Min Range: -6.1056

Max Act: 5.9849. Min Act: -0.0000

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 6.1056. Min Range: -6.1056

Max Act: 5.7882. Min Act: -0.0000

Data Index: 223141 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 6.1056. Min Range: -6.1056

Max Act: 5.6107. Min Act: -0.0000

Data Index: 1007800 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 6.1056. Min Range: -6.1056

Max Act: 5.3960. Min Act: 0.0000

Data Index: 663442 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 6.1056. Min Range: -6.1056

Max Act: 5.1133. Min Act: -0.0000

Data Index: 583515 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.9063. Min Act: -0.0000

Data Index: 54713 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.8104. Min Act: -0.0000

Data Index: 19188 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.5841. Min Act: -0.0000

Data Index: 67817 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.5467. Min Act: -0.0000

Data Index: 862745 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.3319. Min Act: -0.0000

Data Index: 1209477 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.2581. Min Act: -0.0000

Data Index: 781093 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.2631. Min Act: -0.0000

Data Index: 558196 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.0957. Min Act: -0.0000

Data Index: 1309274 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.0658. Min Act: -0.0000

Data Index: 526241 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 6.1056. Min Range: -6.1056

Max Act: 3.8590. Min Act: -0.0000

Data Index: 41147 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 6.1056. Min Range: -6.1056

Max Act: 3.8734. Min Act: -0.0000

Data Index: 999661 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.0172. Min Act: -0.0000

Data Index: 990365 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 6.1056. Min Range: -6.1056

Max Act: 4.2032. Min Act: -0.0000

Data Index: 960070 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 6.1056. Min Range: -6.1056

Max Act: 3.9898. Min Act: -0.0000

Data Index: 432085 (C4 (Web Text))

Max Activating Token Index: 727