Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 978 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.3285. Min Act: -0.0005

Data Index: 694106 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.3151. Min Act: -0.0005

Data Index: 454076 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2880. Min Act: -0.0005

Data Index: 964239 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.3154. Min Act: -0.0004

Data Index: 220510 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2851. Min Act: -0.0005

Data Index: 592264 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2837. Min Act: -0.0005

Data Index: 268810 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2848. Min Act: -0.0005

Data Index: 709158 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2953. Min Act: -0.0005

Data Index: 20580 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2939. Min Act: -0.0005

Data Index: 661051 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2836. Min Act: -0.0005

Data Index: 1101791 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.3010. Min Act: -0.0005

Data Index: 1132224 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2888. Min Act: -0.0005

Data Index: 1200902 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2739. Min Act: -0.0005

Data Index: 1012318 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2943. Min Act: -0.0005

Data Index: 17610 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2850. Min Act: -0.0005

Data Index: 983431 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2870. Min Act: -0.0005

Data Index: 85063 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2927. Min Act: -0.0005

Data Index: 1337702 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2919. Min Act: -0.0005

Data Index: 1208827 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2797. Min Act: -0.0005

Data Index: 1316185 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.3285. Min Range: -0.3285

Max Act: 0.2800. Min Act: -0.0005

Data Index: 517440 (C4 (Web Text))

Max Activating Token Index: 143