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

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

Neuron 3402 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: 1.8034. Min Range: -1.8034

Max Act: 1.8034. Min Act: -0.0000

Data Index: 1548791 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.7139. Min Act: -0.0000

Data Index: 1638728 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.5830. Min Act: -0.0000

Data Index: 1251171 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.5919. Min Act: -0.0000

Data Index: 357347 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3752. Min Act: -0.0000

Data Index: 929337 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.4502. Min Act: -0.0000

Data Index: 1179275 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.4538. Min Act: -0.0000

Data Index: 1005719 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.4495. Min Act: -0.0000

Data Index: 699031 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.4013. Min Act: -0.0000

Data Index: 859419 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3478. Min Act: -0.0000

Data Index: 528011 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1014935 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.4129. Min Act: -0.0000

Data Index: 1499016 (Python Code)

Max Activating Token Index: 277

Text #12

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.2490. Min Act: -0.0000

Data Index: 660022 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3126. Min Act: -0.0000

Data Index: 973713 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3528. Min Act: -0.0000

Data Index: 384498 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.2882. Min Act: -0.0000

Data Index: 231086 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.3363. Min Act: -0.0000

Data Index: 438643 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.2606. Min Act: -0.0000

Data Index: 898432 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.2045. Min Act: -0.0000

Data Index: 374899 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.8034. Min Range: -1.8034

Max Act: 1.2381. Min Act: -0.0000

Data Index: 394391 (C4 (Web Text))

Max Activating Token Index: 927