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

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

Neuron 5087 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7046. Min Range: -3.7046

Max Act: 3.7046. Min Act: -0.0000

Data Index: 237257 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.8539. Min Act: -0.0000

Data Index: 300192 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.7717. Min Act: -0.0000

Data Index: 765439 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.7661. Min Act: -0.0000

Data Index: 955798 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.5995. Min Act: -0.0000

Data Index: 34345 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.6848. Min Act: -0.0000

Data Index: 838727 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.5148. Min Act: -0.0000

Data Index: 1088751 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.7392. Min Act: -0.0000

Data Index: 942761 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.5265. Min Act: -0.0000

Data Index: 1284212 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.6634. Min Act: -0.0000

Data Index: 608375 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.5208. Min Act: -0.0000

Data Index: 1331576 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.5163. Min Act: -0.0000

Data Index: 7931 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.4661. Min Act: -0.0000

Data Index: 328089 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.4330. Min Act: -0.0000

Data Index: 1312365 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.4231. Min Act: -0.0000

Data Index: 386897 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.5367. Min Act: -0.0000

Data Index: 1089659 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.4181. Min Act: -0.0000

Data Index: 1096922 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.3636. Min Act: -0.0000

Data Index: 744515 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.3137. Min Act: -0.0000

Data Index: 1037079 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 3.7046. Min Range: -3.7046

Max Act: 2.4015. Min Act: -0.0000

Data Index: 779237 (C4 (Web Text))

Max Activating Token Index: 301