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

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

Neuron 1005 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0000

Data Index: 276690 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9953. Min Act: -0.0000

Data Index: 13406 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9579. Min Act: -0.0000

Data Index: 778943 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1002214 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8891. Min Act: -0.0000

Data Index: 595594 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8538. Min Act: -0.0000

Data Index: 162452 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1287968 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1277466 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7809. Min Act: -0.0000

Data Index: 564029 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8379. Min Act: -0.0000

Data Index: 918562 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8295. Min Act: -0.0000

Data Index: 872890 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7981. Min Act: -0.0000

Data Index: 231293 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8206. Min Act: -0.0000

Data Index: 122802 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8121. Min Act: -0.0000

Data Index: 955059 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8115. Min Act: -0.0000

Data Index: 417538 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1048360 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1239 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1270653 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1006732 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1147912 (C4 (Web Text))

Max Activating Token Index: 595