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

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

Neuron 4535 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: 0.1375. Min Range: -0.1375

Max Act: 0.1375. Min Act: -0.0000

Data Index: 721260 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1100. Min Act: -0.0000

Data Index: 620004 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1182. Min Act: -0.0000

Data Index: 333801 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1138. Min Act: -0.0000

Data Index: 136190 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1157. Min Act: -0.0000

Data Index: 367050 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1053. Min Act: -0.0000

Data Index: 831577 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1048. Min Act: -0.0000

Data Index: 41915 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1169774 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0986. Min Act: -0.0000

Data Index: 820107 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0943. Min Act: -0.0000

Data Index: 454991 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0996. Min Act: -0.0000

Data Index: 555580 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.1008. Min Act: -0.0000

Data Index: 367081 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0953. Min Act: -0.0000

Data Index: 763373 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0951. Min Act: -0.0000

Data Index: 139771 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1247296 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0924. Min Act: -0.0000

Data Index: 400172 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0885. Min Act: -0.0000

Data Index: 45084 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0873. Min Act: -0.0000

Data Index: 769757 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0933. Min Act: -0.0000

Data Index: 550389 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.1375. Min Range: -0.1375

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1306722 (C4 (Web Text))

Max Activating Token Index: 75