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

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

Neuron 1399 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: 2.5003. Min Range: -2.5003

Max Act: 2.5003. Min Act: -0.0003

Data Index: 1139218 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 2.5003. Min Range: -2.5003

Max Act: 2.3915. Min Act: -0.0002

Data Index: 1293431 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 2.5003. Min Range: -2.5003

Max Act: 2.1383. Min Act: -0.0002

Data Index: 828822 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 2.5003. Min Range: -2.5003

Max Act: 2.1988. Min Act: -0.0002

Data Index: 524584 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 2.5003. Min Range: -2.5003

Max Act: 2.1634. Min Act: -0.0002

Data Index: 477188 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 2.5003. Min Range: -2.5003

Max Act: 2.1261. Min Act: -0.0002

Data Index: 472388 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 2.5003. Min Range: -2.5003

Max Act: 2.1897. Min Act: -0.0002

Data Index: 491373 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.9904. Min Act: -0.0002

Data Index: 876379 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 2.5003. Min Range: -2.5003

Max Act: 2.0069. Min Act: -0.0002

Data Index: 720418 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.9219. Min Act: -0.0002

Data Index: 413040 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.9513. Min Act: -0.0002

Data Index: 234112 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.9733. Min Act: -0.0002

Data Index: 17395 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.9936. Min Act: -0.0002

Data Index: 317715 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 2.5003. Min Range: -2.5003

Max Act: 2.0166. Min Act: -0.0002

Data Index: 1126083 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.9268. Min Act: -0.0002

Data Index: 556436 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.8543. Min Act: -0.0002

Data Index: 819812 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.9138. Min Act: -0.0002

Data Index: 120479 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.8226. Min Act: -0.0002

Data Index: 956867 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.8843. Min Act: -0.0002

Data Index: 1085113 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 2.5003. Min Range: -2.5003

Max Act: 1.9134. Min Act: -0.0002

Data Index: 1237116 (C4 (Web Text))

Max Activating Token Index: 306