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

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

Neuron 5950 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8541. Min Act: -0.0002

Data Index: 586421 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8404. Min Act: -0.0002

Data Index: 1130911 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7232. Min Act: -0.0002

Data Index: 1020244 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7097. Min Act: -0.0002

Data Index: 375709 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6738. Min Act: -0.0002

Data Index: 354220 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7023. Min Act: -0.0002

Data Index: 601625 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7162. Min Act: -0.0002

Data Index: 688852 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6638. Min Act: -0.0002

Data Index: 809287 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6748. Min Act: -0.0002

Data Index: 1289842 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6743. Min Act: -0.0002

Data Index: 671268 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6589. Min Act: -0.0002

Data Index: 655190 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6653. Min Act: -0.0002

Data Index: 53822 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6831. Min Act: -0.0002

Data Index: 165339 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6489. Min Act: -0.0002

Data Index: 1208031 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6166. Min Act: -0.0002

Data Index: 909961 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6162. Min Act: -0.0002

Data Index: 834203 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6295. Min Act: -0.0002

Data Index: 942790 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6035. Min Act: -0.0002

Data Index: 21143 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6059. Min Act: -0.0002

Data Index: 330584 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.6201. Min Act: -0.0002

Data Index: 1082112 (C4 (Web Text))

Max Activating Token Index: 201