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

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

Neuron 2702 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1342730 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.8110. Min Act: -0.0000

Data Index: 132251 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1411698 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7725. Min Act: -0.0000

Data Index: 178207 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1520780 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1561222 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7490. Min Act: -0.0000

Data Index: 1335606 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6787. Min Act: -0.0000

Data Index: 27896 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1406946 (Python Code)

Max Activating Token Index: 427

Text #9

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1377826 (Python Code)

Max Activating Token Index: 198

Text #10

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6008. Min Act: -0.0000

Data Index: 926295 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1409537 (Python Code)

Max Activating Token Index: 1000

Text #12

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1420733 (Python Code)

Max Activating Token Index: 530

Text #13

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1219439 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1514008 (Python Code)

Max Activating Token Index: 971

Text #15

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5897. Min Act: -0.0000

Data Index: 513527 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1110830 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5807. Min Act: -0.0000

Data Index: 261467 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5688. Min Act: -0.0000

Data Index: 579999 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5994. Min Act: -0.0000

Data Index: 591688 (C4 (Web Text))

Max Activating Token Index: 881