Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 131 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0501. Min Range: -1.0501

Max Act: 1.0501. Min Act: -0.0001

Data Index: 1174414 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1098293 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.6202. Min Act: -0.0001

Data Index: 140640 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1099535 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.5096. Min Act: -0.0000

Data Index: 461037 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4648. Min Act: -0.0001

Data Index: 209096 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4712. Min Act: -0.0001

Data Index: 1643778 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4152. Min Act: -0.0001

Data Index: 831130 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4161. Min Act: -0.0001

Data Index: 808566 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4453. Min Act: -0.0000

Data Index: 529544 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1163869 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4673. Min Act: -0.0001

Data Index: 715305 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4227. Min Act: -0.0000

Data Index: 970664 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4347. Min Act: -0.0000

Data Index: 745270 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4494. Min Act: -0.0000

Data Index: 885234 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4092. Min Act: -0.0000

Data Index: 442398 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4331. Min Act: -0.0000

Data Index: 412373 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4152. Min Act: -0.0000

Data Index: 426672 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4260. Min Act: -0.0001

Data Index: 912298 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.0501. Min Range: -1.0501

Max Act: 0.4239. Min Act: -0.0001

Data Index: 949081 (C4 (Web Text))

Max Activating Token Index: 807