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

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

Neuron 1014 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: 1.8744. Min Range: -1.8744

Max Act: 1.8744. Min Act: -0.0000

Data Index: 855131 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.6418. Min Act: -0.0000

Data Index: 597586 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.5542. Min Act: 0.0000

Data Index: 1065410 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.5385. Min Act: 0.0000

Data Index: 1530305 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.4599. Min Act: -0.0000

Data Index: 366707 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.5646. Min Act: -0.0000

Data Index: 1049770 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.4902. Min Act: -0.0000

Data Index: 1645675 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.5056. Min Act: -0.0000

Data Index: 688262 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.3883. Min Act: -0.0000

Data Index: 1090489 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.4682. Min Act: -0.0000

Data Index: 1562885 (Python Code)

Max Activating Token Index: 190

Text #10

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1170037 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.4198. Min Act: -0.0000

Data Index: 585685 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.3859. Min Act: -0.0000

Data Index: 537751 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.4698. Min Act: -0.0000

Data Index: 193159 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.4981. Min Act: -0.0000

Data Index: 226023 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.3919. Min Act: -0.0000

Data Index: 1389858 (Python Code)

Max Activating Token Index: 269

Text #16

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.3159. Min Act: -0.0000

Data Index: 1005737 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.2787. Min Act: -0.0000

Data Index: 1631499 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.2775. Min Act: -0.0000

Data Index: 28856 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 1.8744. Min Range: -1.8744

Max Act: 1.3021. Min Act: 0.0000

Data Index: 841838 (C4 (Web Text))

Max Activating Token Index: 951