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

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

Neuron 3126 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: 0.9223. Min Range: -0.9223

Max Act: 0.9223. Min Act: -0.0001

Data Index: 12148 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7876. Min Act: -0.0001

Data Index: 643869 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7537. Min Act: -0.0001

Data Index: 938326 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6778. Min Act: -0.0001

Data Index: 900049 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6834. Min Act: -0.0001

Data Index: 285158 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6713. Min Act: -0.0001

Data Index: 781517 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6624. Min Act: -0.0001

Data Index: 659702 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6357. Min Act: -0.0001

Data Index: 193200 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6304. Min Act: -0.0001

Data Index: 75668 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6339. Min Act: -0.0001

Data Index: 597615 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6317. Min Act: -0.0001

Data Index: 832962 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6293. Min Act: -0.0001

Data Index: 723706 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6310. Min Act: -0.0001

Data Index: 155643 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6188. Min Act: -0.0001

Data Index: 1020573 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6058. Min Act: -0.0001

Data Index: 621112 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6180. Min Act: -0.0001

Data Index: 1046871 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.5953. Min Act: -0.0001

Data Index: 668683 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.5948. Min Act: -0.0001

Data Index: 396971 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.5577. Min Act: -0.0001

Data Index: 1064773 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.5523. Min Act: -0.0001

Data Index: 712084 (C4 (Web Text))

Max Activating Token Index: 546