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

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

Neuron 2677 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.8326. Min Act: -0.0001

Data Index: 683932 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.9109. Min Act: -0.0001

Data Index: 804175 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.8506. Min Act: -0.0001

Data Index: 1286551 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.9147. Min Act: -0.0001

Data Index: 17268 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.8803. Min Act: -0.0001

Data Index: 354067 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.8320. Min Act: -0.0001

Data Index: 1041855 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7404. Min Act: -0.0001

Data Index: 209340 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.8332. Min Act: -0.0001

Data Index: 1181324 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7537. Min Act: -0.0001

Data Index: 820613 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7373. Min Act: -0.0001

Data Index: 484031 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7289. Min Act: -0.0001

Data Index: 945041 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7397. Min Act: -0.0001

Data Index: 959092 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7189. Min Act: -0.0001

Data Index: 374501 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7863. Min Act: -0.0001

Data Index: 594532 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7160. Min Act: -0.0001

Data Index: 65478 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6859. Min Act: -0.0001

Data Index: 832211 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7365. Min Act: -0.0001

Data Index: 216995 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6804. Min Act: -0.0001

Data Index: 965167 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6588. Min Act: -0.0001

Data Index: 623313 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7029. Min Act: -0.0001

Data Index: 631279 (C4 (Web Text))

Max Activating Token Index: 720