Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1784 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.9151. Min Act: -0.0001

Data Index: 295316 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.9074. Min Act: -0.0001

Data Index: 118506 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.7355. Min Act: -0.0001

Data Index: 1168925 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.5731. Min Act: -0.0001

Data Index: 1295197 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.5890. Min Act: -0.0001

Data Index: 1284683 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.7540. Min Act: -0.0001

Data Index: 568992 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.4163. Min Act: -0.0001

Data Index: 1339506 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.5221. Min Act: -0.0001

Data Index: 217684 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.5676. Min Act: -0.0001

Data Index: 666894 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.3570. Min Act: -0.0001

Data Index: 184410 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.4350. Min Act: -0.0001

Data Index: 115703 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.4692. Min Act: -0.0001

Data Index: 719133 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.3658. Min Act: -0.0001

Data Index: 451892 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.3455. Min Act: -0.0001

Data Index: 928628 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.4841. Min Act: -0.0001

Data Index: 645541 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.3413. Min Act: -0.0001

Data Index: 1174523 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.7091. Min Act: -0.0001

Data Index: 307292 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.1593. Min Act: -0.0001

Data Index: 934629 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.2084. Min Act: -0.0001

Data Index: 804882 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.9151. Min Range: -1.9151

Max Act: 1.2827. Min Act: -0.0001

Data Index: 99018 (C4 (Web Text))

Max Activating Token Index: 109