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

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

Neuron 2778 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5003. Min Range: -1.5003

Max Act: 1.5003. Min Act: -0.0001

Data Index: 698068 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.5003. Min Range: -1.5003

Max Act: 1.1810. Min Act: -0.0001

Data Index: 17121 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.5003. Min Range: -1.5003

Max Act: 1.0631. Min Act: -0.0001

Data Index: 432819 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 1.5003. Min Range: -1.5003

Max Act: 1.0008. Min Act: -0.0001

Data Index: 659997 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.9123. Min Act: -0.0001

Data Index: 301486 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.9463. Min Act: -0.0001

Data Index: 910207 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.9314. Min Act: -0.0001

Data Index: 1401761 (Python Code)

Max Activating Token Index: 1021

Text #7

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.8775. Min Act: -0.0001

Data Index: 1350373 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.8634. Min Act: -0.0001

Data Index: 680793 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.9046. Min Act: -0.0001

Data Index: 1376543 (Python Code)

Max Activating Token Index: 588

Text #10

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.9125. Min Act: -0.0001

Data Index: 1463191 (Python Code)

Max Activating Token Index: 323

Text #11

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.9250. Min Act: -0.0001

Data Index: 161046 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.8932. Min Act: -0.0001

Data Index: 389508 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.9204. Min Act: -0.0001

Data Index: 622012 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.8257. Min Act: -0.0001

Data Index: 1173651 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.8133. Min Act: -0.0001

Data Index: 997039 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.8073. Min Act: -0.0001

Data Index: 351415 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.8490. Min Act: -0.0001

Data Index: 609287 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.8144. Min Act: -0.0001

Data Index: 338140 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 1.5003. Min Range: -1.5003

Max Act: 0.8085. Min Act: -0.0001

Data Index: 274965 (C4 (Web Text))

Max Activating Token Index: 401