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

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

Neuron 1888 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: 3.3497. Min Range: -3.3497

Max Act: 3.3497. Min Act: -0.0003

Data Index: 625287 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 3.3497. Min Range: -3.3497

Max Act: 3.2795. Min Act: -0.0002

Data Index: 76582 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.9604. Min Act: -0.0003

Data Index: 238195 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 3.3497. Min Range: -3.3497

Max Act: 3.0330. Min Act: -0.0002

Data Index: 915811 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 3.3497. Min Range: -3.3497

Max Act: 3.0073. Min Act: -0.0002

Data Index: 191991 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.8418. Min Act: -0.0003

Data Index: 214098 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.8752. Min Act: -0.0002

Data Index: 1210725 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.7605. Min Act: -0.0002

Data Index: 580309 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.8069. Min Act: -0.0002

Data Index: 381825 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.8602. Min Act: -0.0002

Data Index: 720204 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.8508. Min Act: -0.0003

Data Index: 589455 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.8235. Min Act: -0.0002

Data Index: 727590 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.8252. Min Act: -0.0002

Data Index: 934191 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.7156. Min Act: -0.0002

Data Index: 584389 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.6768. Min Act: -0.0003

Data Index: 616744 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.7832. Min Act: -0.0002

Data Index: 1083997 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.7317. Min Act: -0.0002

Data Index: 511315 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.6973. Min Act: -0.0002

Data Index: 279160 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.7113. Min Act: -0.0002

Data Index: 325420 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 3.3497. Min Range: -3.3497

Max Act: 2.5807. Min Act: -0.0002

Data Index: 586343 (C4 (Web Text))

Max Activating Token Index: 774