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

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

Neuron 2795 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7126. Min Act: -0.0000

Data Index: 192679 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7440. Min Act: -0.0000

Data Index: 68023 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7453. Min Act: -0.0000

Data Index: 423876 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6223. Min Act: -0.0000

Data Index: 435803 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6446. Min Act: -0.0001

Data Index: 1019993 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6420. Min Act: -0.0000

Data Index: 457034 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6394. Min Act: -0.0000

Data Index: 150427 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6476. Min Act: -0.0000

Data Index: 73999 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1356838 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5985. Min Act: -0.0000

Data Index: 119467 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6167. Min Act: -0.0000

Data Index: 50225 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6145. Min Act: -0.0000

Data Index: 601882 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5898. Min Act: -0.0000

Data Index: 925355 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6320. Min Act: -0.0000

Data Index: 159034 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5817. Min Act: -0.0001

Data Index: 1314990 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5725. Min Act: -0.0000

Data Index: 82333 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5174. Min Act: -0.0000

Data Index: 539677 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5655. Min Act: -0.0001

Data Index: 1179733 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5658. Min Act: -0.0000

Data Index: 78097 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5751. Min Act: -0.0000

Data Index: 679633 (C4 (Web Text))

Max Activating Token Index: 599