Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1832 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.4672. Min Act: -0.0001

Data Index: 565995 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.3437. Min Act: -0.0001

Data Index: 961444 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.2755. Min Act: -0.0001

Data Index: 398452 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.2346. Min Act: -0.0001

Data Index: 1346042 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1908. Min Act: -0.0001

Data Index: 280827 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.2489. Min Act: -0.0001

Data Index: 665213 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1340. Min Act: -0.0001

Data Index: 82946 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1690. Min Act: -0.0001

Data Index: 736758 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0724. Min Act: -0.0001

Data Index: 12554 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1667. Min Act: -0.0001

Data Index: 178624 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1100. Min Act: -0.0001

Data Index: 297559 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0692. Min Act: -0.0001

Data Index: 76439 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0762. Min Act: -0.0001

Data Index: 368255 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0345. Min Act: -0.0001

Data Index: 1333790 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0320. Min Act: -0.0001

Data Index: 1162380 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.4672. Min Range: -1.4672

Max Act: 0.9765. Min Act: -0.0001

Data Index: 579761 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0751. Min Act: -0.0001

Data Index: 693961 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.4672. Min Range: -1.4672

Max Act: 0.9778. Min Act: -0.0001

Data Index: 144524 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0111. Min Act: -0.0001

Data Index: 931059 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0200. Min Act: -0.0001

Data Index: 862126 (C4 (Web Text))

Max Activating Token Index: 924