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

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

Neuron 3134 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: 1.4135. Min Range: -1.4135

Max Act: 1.4135. Min Act: -0.0002

Data Index: 147367 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.4006. Min Act: -0.0002

Data Index: 1266483 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3845. Min Act: -0.0002

Data Index: 1290196 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3706. Min Act: -0.0002

Data Index: 996726 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3851. Min Act: -0.0002

Data Index: 1298326 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3640. Min Act: -0.0002

Data Index: 490148 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3720. Min Act: -0.0002

Data Index: 550905 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3761. Min Act: -0.0002

Data Index: 979423 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3562. Min Act: -0.0002

Data Index: 1320930 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3337. Min Act: -0.0002

Data Index: 748704 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3242. Min Act: -0.0002

Data Index: 240142 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3488. Min Act: -0.0002

Data Index: 903356 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3246. Min Act: -0.0002

Data Index: 1075943 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.2982. Min Act: -0.0002

Data Index: 349216 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.3310. Min Act: -0.0002

Data Index: 977757 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.2966. Min Act: -0.0002

Data Index: 897209 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.2826. Min Act: -0.0002

Data Index: 1000698 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.2774. Min Act: -0.0002

Data Index: 523948 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.2816. Min Act: -0.0002

Data Index: 359432 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 1.4135. Min Range: -1.4135

Max Act: 1.2932. Min Act: -0.0002

Data Index: 268562 (C4 (Web Text))

Max Activating Token Index: 360