Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1622 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3181. Min Act: -0.0003

Data Index: 1316488 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3233. Min Act: -0.0003

Data Index: 1335261 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2902. Min Act: -0.0003

Data Index: 1068180 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3436. Min Act: -0.0003

Data Index: 797255 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2898. Min Act: -0.0003

Data Index: 240110 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3517. Min Act: -0.0003

Data Index: 554189 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3252. Min Act: -0.0003

Data Index: 673569 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3229. Min Act: -0.0003

Data Index: 830858 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3091. Min Act: -0.0003

Data Index: 1068558 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2856. Min Act: -0.0003

Data Index: 161908 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3063. Min Act: -0.0003

Data Index: 1002205 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2909. Min Act: -0.0003

Data Index: 725330 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2956. Min Act: -0.0003

Data Index: 139357 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3021. Min Act: -0.0003

Data Index: 541012 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3011. Min Act: -0.0003

Data Index: 657795 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2989. Min Act: -0.0003

Data Index: 672719 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2882. Min Act: -0.0003

Data Index: 562023 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2967. Min Act: -0.0003

Data Index: 249558 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2950. Min Act: -0.0003

Data Index: 22482 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2844. Min Act: -0.0003

Data Index: 916088 (C4 (Web Text))

Max Activating Token Index: 222