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

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

Neuron 3571 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3632. Min Act: -0.0002

Data Index: 358805 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3278. Min Act: -0.0002

Data Index: 544808 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3236. Min Act: -0.0002

Data Index: 43320 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3142. Min Act: -0.0002

Data Index: 1080233 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3171. Min Act: -0.0002

Data Index: 698327 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3160. Min Act: -0.0002

Data Index: 700825 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3058. Min Act: -0.0002

Data Index: 872652 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2928. Min Act: -0.0002

Data Index: 601892 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2789. Min Act: -0.0002

Data Index: 922687 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3051. Min Act: -0.0002

Data Index: 66180 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2939. Min Act: -0.0002

Data Index: 1007746 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2955. Min Act: -0.0002

Data Index: 877264 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2979. Min Act: -0.0002

Data Index: 970191 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2734. Min Act: -0.0002

Data Index: 547320 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2618. Min Act: -0.0002

Data Index: 92547 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2626. Min Act: -0.0002

Data Index: 942328 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2614. Min Act: -0.0002

Data Index: 568662 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2780. Min Act: -0.0002

Data Index: 367516 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2574. Min Act: -0.0002

Data Index: 54672 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2825. Min Act: -0.0002

Data Index: 10436 (C4 (Web Text))

Max Activating Token Index: 312