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

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

Neuron 4635 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: 0.3522. Min Range: -0.3522

Max Act: 0.3522. Min Act: -0.0002

Data Index: 9063 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3442. Min Act: -0.0002

Data Index: 184173 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3514. Min Act: -0.0002

Data Index: 166090 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3379. Min Act: -0.0002

Data Index: 106340 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3372. Min Act: -0.0003

Data Index: 205264 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3260. Min Act: -0.0002

Data Index: 756196 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3214. Min Act: -0.0002

Data Index: 914777 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3179. Min Act: -0.0002

Data Index: 1187673 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3179. Min Act: -0.0002

Data Index: 33724 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3211. Min Act: -0.0002

Data Index: 1085509 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3205. Min Act: -0.0002

Data Index: 835149 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3095. Min Act: -0.0002

Data Index: 334198 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3018. Min Act: -0.0002

Data Index: 22692 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3019. Min Act: -0.0002

Data Index: 614500 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3012. Min Act: -0.0002

Data Index: 805443 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2910. Min Act: -0.0002

Data Index: 682955 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2894. Min Act: -0.0002

Data Index: 242106 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2946. Min Act: -0.0002

Data Index: 1274253 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2933. Min Act: -0.0002

Data Index: 711036 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2894. Min Act: -0.0002

Data Index: 246482 (C4 (Web Text))

Max Activating Token Index: 985