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

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

Neuron 3394 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.5026. Min Act: -0.0001

Data Index: 341225 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4153. Min Act: -0.0001

Data Index: 146700 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4464. Min Act: -0.0001

Data Index: 394027 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4224. Min Act: -0.0000

Data Index: 223534 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1009032 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4022. Min Act: -0.0001

Data Index: 869744 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3778. Min Act: -0.0001

Data Index: 31347 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3540. Min Act: -0.0001

Data Index: 601400 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3652. Min Act: -0.0001

Data Index: 363951 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3436. Min Act: -0.0001

Data Index: 546273 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3137. Min Act: -0.0001

Data Index: 108642 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3290. Min Act: -0.0001

Data Index: 372393 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.2865. Min Act: -0.0001

Data Index: 34756 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3126. Min Act: -0.0001

Data Index: 977547 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3029. Min Act: -0.0000

Data Index: 940069 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.2767. Min Act: -0.0000

Data Index: 754024 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.2982. Min Act: -0.0001

Data Index: 165061 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.2788. Min Act: -0.0000

Data Index: 371063 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.2599. Min Act: -0.0001

Data Index: 757868 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.2713. Min Act: -0.0000

Data Index: 267873 (C4 (Web Text))

Max Activating Token Index: 690