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

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

Neuron 2829 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1724. Min Act: -0.0000

Data Index: 902001 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.3027. Min Act: -0.0000

Data Index: 56515 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2917. Min Act: -0.0000

Data Index: 304832 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.8597. Min Act: -0.0000

Data Index: 320981 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.8167. Min Act: -0.0000

Data Index: 249378 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.9325. Min Act: -0.0000

Data Index: 463267 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.7057. Min Act: -0.0000

Data Index: 138095 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.8794. Min Act: -0.0000

Data Index: 1079044 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.6846. Min Act: -0.0000

Data Index: 980413 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.6739. Min Act: -0.0000

Data Index: 661904 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.5182. Min Act: -0.0000

Data Index: 354999 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.6512. Min Act: -0.0000

Data Index: 686827 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.5250. Min Act: -0.0000

Data Index: 23909 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.5038. Min Act: -0.0000

Data Index: 567856 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.3749. Min Act: -0.0000

Data Index: 765605 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.3681. Min Act: -0.0000

Data Index: 1032022 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.3171. Min Act: -0.0000

Data Index: 163610 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.3429. Min Act: -0.0000

Data Index: 1038041 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.3145. Min Act: -0.0000

Data Index: 990787 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 3.3027. Min Range: -3.3027

Max Act: 2.3245. Min Act: -0.0000

Data Index: 495441 (C4 (Web Text))

Max Activating Token Index: 188