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

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

Neuron 4886 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.6158. Min Act: -0.0000

Data Index: 691111 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5247. Min Act: -0.0000

Data Index: 97252 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1420336 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5420. Min Act: -0.0000

Data Index: 687941 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4977. Min Act: -0.0000

Data Index: 537384 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4800. Min Act: -0.0000

Data Index: 950236 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1493672 (Python Code)

Max Activating Token Index: 357

Text #7

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1422218 (Python Code)

Max Activating Token Index: 485

Text #8

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1231487 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4998. Min Act: -0.0000

Data Index: 929059 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1550331 (Python Code)

Max Activating Token Index: 415

Text #11

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1633357 (Python Code)

Max Activating Token Index: 658

Text #12

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1634103 (Python Code)

Max Activating Token Index: 644

Text #13

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5086. Min Act: -0.0000

Data Index: 446678 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1505151 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1112783 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4571. Min Act: -0.0000

Data Index: 948247 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1096020 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1538093 (Python Code)

Max Activating Token Index: 196

Text #19

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1084893 (C4 (Web Text))

Max Activating Token Index: 731