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

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

Neuron 3794 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.5371. Min Act: -0.0002

Data Index: 238456 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.5289. Min Act: -0.0002

Data Index: 220261 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.5336. Min Act: -0.0002

Data Index: 692158 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4909. Min Act: -0.0002

Data Index: 164843 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4906. Min Act: -0.0002

Data Index: 1177296 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.5014. Min Act: -0.0002

Data Index: 145362 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4800. Min Act: -0.0002

Data Index: 934020 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4694. Min Act: -0.0002

Data Index: 269325 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4681. Min Act: -0.0002

Data Index: 767089 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4714. Min Act: -0.0002

Data Index: 898084 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4548. Min Act: -0.0002

Data Index: 922801 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4607. Min Act: -0.0002

Data Index: 922454 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4562. Min Act: -0.0002

Data Index: 161306 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4537. Min Act: -0.0002

Data Index: 136966 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4624. Min Act: -0.0002

Data Index: 343193 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4464. Min Act: -0.0002

Data Index: 396128 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4455. Min Act: -0.0003

Data Index: 710184 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4447. Min Act: -0.0002

Data Index: 615805 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4521. Min Act: -0.0002

Data Index: 517865 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4384. Min Act: -0.0002

Data Index: 978104 (C4 (Web Text))

Max Activating Token Index: 907