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

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

Neuron 4470 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: 0.3933. Min Range: -0.3933

Max Act: 0.3933. Min Act: -0.0002

Data Index: 141578 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3781. Min Act: -0.0002

Data Index: 44628 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3720. Min Act: -0.0002

Data Index: 640494 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3726. Min Act: -0.0002

Data Index: 821336 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3337. Min Act: -0.0002

Data Index: 741499 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3324. Min Act: -0.0002

Data Index: 650448 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3215. Min Act: -0.0002

Data Index: 1086701 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3102. Min Act: -0.0002

Data Index: 266094 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3074. Min Act: -0.0002

Data Index: 518384 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3139. Min Act: -0.0002

Data Index: 10869 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2822. Min Act: -0.0002

Data Index: 307695 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3210. Min Act: -0.0002

Data Index: 1073569 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3216. Min Act: -0.0002

Data Index: 926884 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3008. Min Act: -0.0002

Data Index: 185135 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3092. Min Act: -0.0002

Data Index: 559828 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3095. Min Act: -0.0002

Data Index: 503529 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2892. Min Act: -0.0002

Data Index: 757846 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3054. Min Act: -0.0002

Data Index: 456902 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3149. Min Act: -0.0002

Data Index: 145700 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3049. Min Act: -0.0002

Data Index: 1054606 (C4 (Web Text))

Max Activating Token Index: 51