Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2780 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1452. Min Act: -0.0003

Data Index: 203998 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1244. Min Act: -0.0003

Data Index: 718652 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1181. Min Act: -0.0003

Data Index: 715077 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1223. Min Act: -0.0003

Data Index: 995689 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1132. Min Act: -0.0003

Data Index: 1182694 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1086. Min Act: -0.0003

Data Index: 653802 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1116. Min Act: -0.0004

Data Index: 1019077 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1141. Min Act: -0.0003

Data Index: 664269 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1020. Min Act: -0.0003

Data Index: 1247241 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1091. Min Act: -0.0003

Data Index: 1173543 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1086. Min Act: -0.0003

Data Index: 855045 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1007. Min Act: -0.0003

Data Index: 349005 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1037. Min Act: -0.0003

Data Index: 951490 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1032. Min Act: -0.0003

Data Index: 675383 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1013. Min Act: -0.0003

Data Index: 796263 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1007. Min Act: -0.0003

Data Index: 779494 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1027. Min Act: -0.0004

Data Index: 989383 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1027. Min Act: -0.0003

Data Index: 113112 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0929. Min Act: -0.0003

Data Index: 500737 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0982. Min Act: -0.0003

Data Index: 220049 (C4 (Web Text))

Max Activating Token Index: 905