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

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

Neuron 657 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9050. Min Range: -3.9050

Max Act: 3.9050. Min Act: -0.0000

Data Index: 372400 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.8972. Min Act: -0.0000

Data Index: 698158 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.6510. Min Act: -0.0000

Data Index: 197961 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 3.9050. Min Range: -3.9050

Max Act: 3.0096. Min Act: -0.0000

Data Index: 670407 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.7354. Min Act: -0.0000

Data Index: 579403 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.5781. Min Act: -0.0000

Data Index: 79977 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.8305. Min Act: -0.0000

Data Index: 335436 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.6817. Min Act: -0.0000

Data Index: 549883 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.6687. Min Act: -0.0000

Data Index: 334754 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.1406. Min Act: -0.0000

Data Index: 1221621 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.5974. Min Act: -0.0000

Data Index: 1259388 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.5917. Min Act: -0.0000

Data Index: 924375 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.2514. Min Act: -0.0000

Data Index: 395162 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.4725. Min Act: -0.0000

Data Index: 846198 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.5902. Min Act: -0.0000

Data Index: 95971 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.5819. Min Act: -0.0000

Data Index: 230521 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.4249. Min Act: -0.0000

Data Index: 416412 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.6168. Min Act: -0.0000

Data Index: 1284447 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.4857. Min Act: -0.0000

Data Index: 495889 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 3.9050. Min Range: -3.9050

Max Act: 2.0181. Min Act: -0.0000

Data Index: 13057 (C4 (Web Text))

Max Activating Token Index: 832