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

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

Neuron 955 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: 2.2557. Min Range: -2.2557

Max Act: 2.2557. Min Act: -0.0002

Data Index: 478271 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 2.2557. Min Range: -2.2557

Max Act: 2.1670. Min Act: -0.0002

Data Index: 762052 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 2.2557. Min Range: -2.2557

Max Act: 2.1795. Min Act: -0.0002

Data Index: 978654 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 2.2557. Min Range: -2.2557

Max Act: 2.0626. Min Act: -0.0002

Data Index: 284246 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 2.2557. Min Range: -2.2557

Max Act: 2.0288. Min Act: -0.0002

Data Index: 525075 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 2.2557. Min Range: -2.2557

Max Act: 2.0482. Min Act: -0.0002

Data Index: 590917 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 2.2557. Min Range: -2.2557

Max Act: 2.0574. Min Act: -0.0002

Data Index: 912065 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 2.2557. Min Range: -2.2557

Max Act: 2.0441. Min Act: -0.0003

Data Index: 617329 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 2.2557. Min Range: -2.2557

Max Act: 2.0709. Min Act: -0.0002

Data Index: 245028 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 2.2557. Min Range: -2.2557

Max Act: 2.0083. Min Act: -0.0002

Data Index: 439642 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 2.2557. Min Range: -2.2557

Max Act: 1.9860. Min Act: -0.0002

Data Index: 903692 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 2.2557. Min Range: -2.2557

Max Act: 2.0249. Min Act: -0.0002

Data Index: 663141 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 2.2557. Min Range: -2.2557

Max Act: 1.9538. Min Act: -0.0002

Data Index: 290256 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 2.2557. Min Range: -2.2557

Max Act: 1.9633. Min Act: -0.0003

Data Index: 370153 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 2.2557. Min Range: -2.2557

Max Act: 1.9307. Min Act: -0.0003

Data Index: 824864 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 2.2557. Min Range: -2.2557

Max Act: 1.9381. Min Act: -0.0002

Data Index: 1355852 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 2.2557. Min Range: -2.2557

Max Act: 1.8492. Min Act: -0.0002

Data Index: 141063 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 2.2557. Min Range: -2.2557

Max Act: 1.8077. Min Act: -0.0002

Data Index: 911466 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 2.2557. Min Range: -2.2557

Max Act: 1.7811. Min Act: -0.0002

Data Index: 329247 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 2.2557. Min Range: -2.2557

Max Act: 1.7634. Min Act: -0.0002

Data Index: 283759 (C4 (Web Text))

Max Activating Token Index: 304