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

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

Neuron 656 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5294. Min Act: -0.0000

Data Index: 27606 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5070. Min Act: -0.0000

Data Index: 181045 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4347. Min Act: -0.0000

Data Index: 620997 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4228. Min Act: -0.0000

Data Index: 684723 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3505. Min Act: -0.0000

Data Index: 140675 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3918. Min Act: -0.0000

Data Index: 925536 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3434. Min Act: -0.0000

Data Index: 337417 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1347294 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3687. Min Act: -0.0000

Data Index: 453201 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3374. Min Act: -0.0000

Data Index: 102883 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.2967. Min Act: -0.0000

Data Index: 490609 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1359590 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1149778 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1121654 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1065998 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3337. Min Act: -0.0000

Data Index: 656818 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1333906 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1086397 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.2988. Min Act: -0.0000

Data Index: 109701 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3091. Min Act: -0.0000

Data Index: 344618 (C4 (Web Text))

Max Activating Token Index: 455