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

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

Neuron 4579 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: 2.0158. Min Range: -2.0158

Max Act: 2.0158. Min Act: -0.0002

Data Index: 1011573 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.9649. Min Act: -0.0002

Data Index: 1156811 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.9576. Min Act: -0.0002

Data Index: 24334 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.8927. Min Act: -0.0002

Data Index: 1133891 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.8389. Min Act: -0.0002

Data Index: 1088692 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.8629. Min Act: -0.0002

Data Index: 112711 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.7441. Min Act: -0.0002

Data Index: 248680 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.7114. Min Act: -0.0003

Data Index: 723741 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.7125. Min Act: -0.0002

Data Index: 1297849 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.7050. Min Act: -0.0002

Data Index: 136245 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.6545. Min Act: -0.0002

Data Index: 896579 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.6638. Min Act: -0.0002

Data Index: 817416 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.6513. Min Act: -0.0002

Data Index: 1032709 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.6481. Min Act: -0.0002

Data Index: 826798 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.6343. Min Act: -0.0002

Data Index: 138762 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.6275. Min Act: -0.0002

Data Index: 936607 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.6449. Min Act: -0.0002

Data Index: 845970 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.6432. Min Act: -0.0002

Data Index: 1319486 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.6227. Min Act: -0.0002

Data Index: 664409 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 2.0158. Min Range: -2.0158

Max Act: 1.6107. Min Act: -0.0002

Data Index: 1083517 (C4 (Web Text))

Max Activating Token Index: 201