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

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

Neuron 1039 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0244. Min Range: -1.0244

Max Act: 1.0244. Min Act: -0.0001

Data Index: 780882 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.8314. Min Act: -0.0001

Data Index: 826320 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.6339. Min Act: -0.0001

Data Index: 1247615 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7046. Min Act: -0.0000

Data Index: 138935 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.6621. Min Act: -0.0000

Data Index: 77123 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.6143. Min Act: -0.0001

Data Index: 556555 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.6494. Min Act: -0.0001

Data Index: 448273 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.6168. Min Act: -0.0001

Data Index: 778015 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.5948. Min Act: -0.0000

Data Index: 882170 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1169138 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1031748 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.5835. Min Act: -0.0001

Data Index: 477601 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.5659. Min Act: -0.0000

Data Index: 580642 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.5643. Min Act: -0.0001

Data Index: 942481 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.5534. Min Act: -0.0000

Data Index: 670516 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.5197. Min Act: -0.0001

Data Index: 1225339 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.6043. Min Act: -0.0000

Data Index: 443082 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1222347 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.5604. Min Act: -0.0000

Data Index: 459197 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1221483 (C4 (Web Text))

Max Activating Token Index: 645