Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 342 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6108. Min Range: -3.6108

Max Act: 3.6108. Min Act: -0.0001

Data Index: 654153 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.4772. Min Act: -0.0001

Data Index: 1298192 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.3130. Min Act: -0.0001

Data Index: 170115 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.2847. Min Act: -0.0001

Data Index: 774948 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.1046. Min Act: -0.0001

Data Index: 52331 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.2053. Min Act: -0.0001

Data Index: 530494 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.3181. Min Act: -0.0001

Data Index: 307613 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.4261. Min Act: -0.0001

Data Index: 355998 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.3943. Min Act: -0.0001

Data Index: 951921 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.2483. Min Act: -0.0001

Data Index: 1266017 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.0894. Min Act: -0.0001

Data Index: 1337942 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.1016. Min Act: -0.0001

Data Index: 617997 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.1933. Min Act: -0.0001

Data Index: 194445 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.0706. Min Act: -0.0001

Data Index: 204664 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.0517. Min Act: -0.0001

Data Index: 178434 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 3.6108. Min Range: -3.6108

Max Act: 2.0375. Min Act: -0.0001

Data Index: 1281093 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 3.6108. Min Range: -3.6108

Max Act: 1.9555. Min Act: -0.0001

Data Index: 887964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.6108. Min Range: -3.6108

Max Act: 1.8286. Min Act: -0.0001

Data Index: 1282055 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 3.6108. Min Range: -3.6108

Max Act: 1.9217. Min Act: -0.0001

Data Index: 1255149 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 3.6108. Min Range: -3.6108

Max Act: 1.9999. Min Act: -0.0001

Data Index: 1192618 (C4 (Web Text))

Max Activating Token Index: 947