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

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

Neuron 1122 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.7073. Min Act: -0.0000

Data Index: 262627 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1417 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5393. Min Act: -0.0000

Data Index: 865116 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5288. Min Act: -0.0000

Data Index: 964997 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5376. Min Act: -0.0000

Data Index: 934432 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5297. Min Act: -0.0000

Data Index: 695941 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5130. Min Act: 0.0001

Data Index: 1064122 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1340310 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1359561 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4983. Min Act: -0.0000

Data Index: 608974 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4672. Min Act: -0.0000

Data Index: 168976 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4541. Min Act: -0.0000

Data Index: 530158 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4717. Min Act: -0.0000

Data Index: 561318 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4719. Min Act: -0.0000

Data Index: 40362 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1157407 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1261752 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4411. Min Act: -0.0000

Data Index: 767324 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4552. Min Act: -0.0000

Data Index: 400316 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1226137 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.4378. Min Act: -0.0000

Data Index: 576271 (C4 (Web Text))

Max Activating Token Index: 127