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

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

Neuron 126 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: 1.2603. Min Range: -1.2603

Max Act: 1.2603. Min Act: -0.0001

Data Index: 1163467 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.1355. Min Act: -0.0001

Data Index: 899639 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.0567. Min Act: -0.0001

Data Index: 317438 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.9404. Min Act: -0.0001

Data Index: 903988 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8477. Min Act: -0.0001

Data Index: 210588 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8491. Min Act: -0.0001

Data Index: 928008 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7979. Min Act: -0.0001

Data Index: 313454 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7908. Min Act: -0.0001

Data Index: 683015 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7546. Min Act: -0.0001

Data Index: 217275 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8000. Min Act: -0.0001

Data Index: 962125 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7581. Min Act: -0.0001

Data Index: 623610 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7431. Min Act: -0.0001

Data Index: 766685 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7815. Min Act: -0.0001

Data Index: 135975 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7228. Min Act: -0.0001

Data Index: 376301 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7186. Min Act: -0.0001

Data Index: 657997 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7356. Min Act: -0.0001

Data Index: 297467 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7341. Min Act: -0.0001

Data Index: 1193403 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7082. Min Act: -0.0001

Data Index: 247223 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.6884. Min Act: -0.0001

Data Index: 975074 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.6939. Min Act: -0.0001

Data Index: 1143240 (C4 (Web Text))

Max Activating Token Index: 611