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

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

Neuron 4485 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8102. Min Range: -4.8102

Max Act: 4.8102. Min Act: -0.0000

Data Index: 1293473 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 4.8102. Min Range: -4.8102

Max Act: 4.2856. Min Act: -0.0000

Data Index: 289319 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.8982. Min Act: -0.0000

Data Index: 1319928 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.7293. Min Act: -0.0000

Data Index: 104360 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.6947. Min Act: -0.0000

Data Index: 169772 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.5403. Min Act: -0.0000

Data Index: 20298 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.4788. Min Act: -0.0000

Data Index: 975991 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.6192. Min Act: -0.0000

Data Index: 849011 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.3147. Min Act: -0.0000

Data Index: 257607 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.7699. Min Act: -0.0000

Data Index: 359104 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.8822. Min Act: -0.0000

Data Index: 469184 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.8932. Min Act: -0.0000

Data Index: 1181350 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.2973. Min Act: -0.0000

Data Index: 781668 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.1620. Min Act: -0.0000

Data Index: 425841 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.5070. Min Act: -0.0000

Data Index: 376414 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.4311. Min Act: -0.0000

Data Index: 120135 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.1086. Min Act: -0.0000

Data Index: 989865 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.1080. Min Act: -0.0000

Data Index: 963871 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.0997. Min Act: -0.0000

Data Index: 161808 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 4.8102. Min Range: -4.8102

Max Act: 3.0970. Min Act: -0.0000

Data Index: 712189 (C4 (Web Text))

Max Activating Token Index: 325