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

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

Neuron 2309 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0279. Min Range: -1.0279

Max Act: 1.0279. Min Act: -0.0001

Data Index: 1132237 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8884. Min Act: -0.0001

Data Index: 186156 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.9034. Min Act: -0.0001

Data Index: 839317 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.9108. Min Act: -0.0001

Data Index: 603734 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.9221. Min Act: -0.0000

Data Index: 643092 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.9196. Min Act: -0.0001

Data Index: 172891 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.9052. Min Act: -0.0001

Data Index: 1204221 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.9381. Min Act: -0.0001

Data Index: 13786 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.9094. Min Act: -0.0001

Data Index: 661087 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8670. Min Act: -0.0001

Data Index: 577414 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.9046. Min Act: -0.0001

Data Index: 125987 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8050. Min Act: -0.0001

Data Index: 390754 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8274. Min Act: -0.0001

Data Index: 104641 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8212. Min Act: -0.0001

Data Index: 772584 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8470. Min Act: -0.0001

Data Index: 1341532 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7954. Min Act: -0.0001

Data Index: 199089 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7923. Min Act: -0.0001

Data Index: 772063 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.7621. Min Act: -0.0001

Data Index: 704607 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8003. Min Act: -0.0001

Data Index: 1002120 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.0279. Min Range: -1.0279

Max Act: 0.8253. Min Act: -0.0001

Data Index: 423410 (C4 (Web Text))

Max Activating Token Index: 552