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

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

Neuron 2952 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1111362 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3034. Min Act: -0.0001

Data Index: 1083353 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3277. Min Act: -0.0001

Data Index: 979750 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3382. Min Act: -0.0001

Data Index: 412278 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3067. Min Act: -0.0001

Data Index: 832092 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1262753 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3177. Min Act: -0.0001

Data Index: 436795 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2995. Min Act: -0.0001

Data Index: 196847 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2841. Min Act: -0.0001

Data Index: 660512 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2973. Min Act: -0.0001

Data Index: 335629 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2739. Min Act: -0.0001

Data Index: 91089 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2972. Min Act: -0.0001

Data Index: 539275 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2843. Min Act: -0.0001

Data Index: 769818 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3012. Min Act: -0.0001

Data Index: 254119 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2773. Min Act: -0.0001

Data Index: 1080839 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2845. Min Act: -0.0001

Data Index: 63278 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2744. Min Act: -0.0001

Data Index: 676990 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2831. Min Act: -0.0001

Data Index: 1328910 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2925. Min Act: -0.0001

Data Index: 260397 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2703. Min Act: -0.0001

Data Index: 1207747 (C4 (Web Text))

Max Activating Token Index: 63