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

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

Neuron 925 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1467045 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1528807 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1151. Min Act: -0.0000

Data Index: 1018009 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0522. Min Act: -0.0000

Data Index: 1590484 (Python Code)

Max Activating Token Index: 800

Text #4

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.9161. Min Act: 0.0000

Data Index: 713797 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1111859 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.7760. Min Act: -0.0000

Data Index: 909792 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1166600 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.7045. Min Act: -0.0000

Data Index: 1344001 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1105818 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1059552 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.6656. Min Act: -0.0000

Data Index: 263411 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.6688. Min Act: -0.0000

Data Index: 59213 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.6462. Min Act: -0.0000

Data Index: 202477 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.6573. Min Act: 0.0000

Data Index: 728736 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.6272. Min Act: -0.0000

Data Index: 725201 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.6235. Min Act: -0.0000

Data Index: 452764 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.5867. Min Act: -0.0000

Data Index: 28573 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.6258. Min Act: -0.0000

Data Index: 965666 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.6237. Min Act: -0.0000

Data Index: 511026 (C4 (Web Text))

Max Activating Token Index: 544