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

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

Neuron 4577 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2119. Min Range: -1.2119

Max Act: 1.2119. Min Act: -0.0000

Data Index: 709482 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.2119. Min Range: -1.2119

Max Act: 1.1097. Min Act: -0.0000

Data Index: 775650 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.2119. Min Range: -1.2119

Max Act: 1.0978. Min Act: -0.0000

Data Index: 300984 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 1.2119. Min Range: -1.2119

Max Act: 1.1304. Min Act: -0.0000

Data Index: 1032858 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.2119. Min Range: -1.2119

Max Act: 1.0538. Min Act: -0.0000

Data Index: 1298435 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 1.2119. Min Range: -1.2119

Max Act: 1.0396. Min Act: -0.0000

Data Index: 841858 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 1.2119. Min Range: -1.2119

Max Act: 1.0499. Min Act: -0.0000

Data Index: 411962 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.9922. Min Act: -0.0000

Data Index: 595219 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.9645. Min Act: -0.0000

Data Index: 44211 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.2119. Min Range: -1.2119

Max Act: 1.0000. Min Act: -0.0000

Data Index: 69765 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.9915. Min Act: -0.0000

Data Index: 800291 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.9207. Min Act: -0.0000

Data Index: 853185 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.9600. Min Act: -0.0000

Data Index: 123899 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.8952. Min Act: -0.0000

Data Index: 643196 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1347070 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.9341. Min Act: -0.0000

Data Index: 31595 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.9463. Min Act: -0.0000

Data Index: 690460 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.9113. Min Act: -0.0000

Data Index: 797860 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1269994 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.2119. Min Range: -1.2119

Max Act: 0.9296. Min Act: -0.0000

Data Index: 859464 (C4 (Web Text))

Max Activating Token Index: 718