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

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

Neuron 1133 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.8895. Min Act: -0.0000

Data Index: 1234681 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.8139. Min Act: -0.0000

Data Index: 177139 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.9543. Min Act: -0.0000

Data Index: 931964 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.6188. Min Act: -0.0000

Data Index: 1031031 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.5969. Min Act: -0.0000

Data Index: 208977 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.4420. Min Act: -0.0000

Data Index: 233141 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.5467. Min Act: -0.0000

Data Index: 640377 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.3529. Min Act: -0.0000

Data Index: 1003922 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.6093. Min Act: -0.0000

Data Index: 29704 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.3097. Min Act: -0.0000

Data Index: 774215 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.2993. Min Act: -0.0000

Data Index: 596045 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.4200. Min Act: -0.0000

Data Index: 1308923 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.4070. Min Act: -0.0000

Data Index: 494334 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.3710. Min Act: -0.0000

Data Index: 513971 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.4568. Min Act: -0.0000

Data Index: 230887 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.3266. Min Act: -0.0000

Data Index: 237385 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.3219. Min Act: -0.0000

Data Index: 125663 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.2127. Min Act: -0.0000

Data Index: 208434 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.3252. Min Act: -0.0000

Data Index: 289244 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 2.9543. Min Range: -2.9543

Max Act: 2.3000. Min Act: -0.0000

Data Index: 582463 (C4 (Web Text))

Max Activating Token Index: 1020