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

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

Neuron 3792 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4388. Min Range: -2.4388

Max Act: 2.4388. Min Act: -0.0000

Data Index: 1254039 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 2.4388. Min Range: -2.4388

Max Act: 2.1799. Min Act: -0.0000

Data Index: 748055 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 2.4388. Min Range: -2.4388

Max Act: 2.1649. Min Act: -0.0000

Data Index: 227875 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 2.4388. Min Range: -2.4388

Max Act: 2.2132. Min Act: -0.0000

Data Index: 14416 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.9494. Min Act: 0.0000

Data Index: 1210352 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.8771. Min Act: -0.0000

Data Index: 393227 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.8718. Min Act: -0.0000

Data Index: 473533 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.9565. Min Act: -0.0000

Data Index: 153024 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.8129. Min Act: -0.0000

Data Index: 292143 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.7714. Min Act: -0.0000

Data Index: 22690 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.7772. Min Act: -0.0000

Data Index: 200228 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.6816. Min Act: -0.0000

Data Index: 1328382 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.4305. Min Act: -0.0000

Data Index: 614439 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.6999. Min Act: -0.0000

Data Index: 1250108 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.7168. Min Act: -0.0000

Data Index: 581670 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.6929. Min Act: -0.0000

Data Index: 18667 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.6982. Min Act: -0.0000

Data Index: 794705 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.7830. Min Act: -0.0000

Data Index: 180183 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.5235. Min Act: -0.0000

Data Index: 1130962 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 2.4388. Min Range: -2.4388

Max Act: 1.6880. Min Act: -0.0000

Data Index: 1004204 (C4 (Web Text))

Max Activating Token Index: 220