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

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

Neuron 2552 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1074623 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.4119. Min Act: -0.0001

Data Index: 147305 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3995. Min Act: -0.0002

Data Index: 652080 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3917. Min Act: -0.0002

Data Index: 5255 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3767. Min Act: -0.0001

Data Index: 242305 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1266666 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3408. Min Act: -0.0001

Data Index: 881201 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3078. Min Act: -0.0001

Data Index: 512844 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3426. Min Act: -0.0002

Data Index: 262001 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3284. Min Act: -0.0001

Data Index: 865797 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3232. Min Act: -0.0001

Data Index: 141463 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3455. Min Act: -0.0002

Data Index: 543394 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3030. Min Act: -0.0001

Data Index: 284499 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3099. Min Act: -0.0001

Data Index: 1327229 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2997. Min Act: -0.0001

Data Index: 983829 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.3025. Min Act: -0.0001

Data Index: 1125646 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2840. Min Act: -0.0001

Data Index: 750132 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2803. Min Act: -0.0002

Data Index: 712766 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2970. Min Act: -0.0001

Data Index: 875303 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.4240. Min Range: -0.4240

Max Act: 0.2943. Min Act: -0.0001

Data Index: 628037 (C4 (Web Text))

Max Activating Token Index: 495