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

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

Neuron 1311 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.6585. Min Act: -0.0000

Data Index: 1153202 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.6154. Min Act: -0.0000

Data Index: 1320788 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.5354. Min Act: -0.0000

Data Index: 676798 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.3787. Min Act: -0.0000

Data Index: 258914 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.3483. Min Act: -0.0001

Data Index: 890154 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.2909. Min Act: -0.0000

Data Index: 607928 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.2015. Min Act: -0.0000

Data Index: 564277 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.3144. Min Act: -0.0000

Data Index: 855423 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.2961. Min Act: -0.0000

Data Index: 160928 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1322408 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.2042. Min Act: -0.0000

Data Index: 861345 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1150766 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.1402. Min Act: -0.0000

Data Index: 270821 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.0061. Min Act: -0.0000

Data Index: 162181 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.2896. Min Act: -0.0000

Data Index: 1208362 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.1254. Min Act: -0.0000

Data Index: 267531 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.1269. Min Act: -0.0000

Data Index: 482660 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1111693 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1147051 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 1.6585. Min Range: -1.6585

Max Act: 1.0603. Min Act: -0.0000

Data Index: 46004 (C4 (Web Text))

Max Activating Token Index: 267