Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3137 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.7236. Min Act: -0.0001

Data Index: 566539 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6854. Min Act: -0.0001

Data Index: 506014 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.7032. Min Act: -0.0001

Data Index: 407474 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.7199. Min Act: -0.0001

Data Index: 357747 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6995. Min Act: -0.0001

Data Index: 429915 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6692. Min Act: -0.0001

Data Index: 179570 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6642. Min Act: -0.0001

Data Index: 433901 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6049. Min Act: -0.0001

Data Index: 218588 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6718. Min Act: -0.0001

Data Index: 734334 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6551. Min Act: -0.0001

Data Index: 659984 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6177. Min Act: -0.0001

Data Index: 1936 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6478. Min Act: -0.0001

Data Index: 593381 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6288. Min Act: -0.0000

Data Index: 147760 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1038189 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6423. Min Act: -0.0001

Data Index: 744804 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6379. Min Act: -0.0001

Data Index: 1250097 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6363. Min Act: -0.0001

Data Index: 776218 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6004. Min Act: -0.0001

Data Index: 487483 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6374. Min Act: -0.0001

Data Index: 115195 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6134. Min Act: -0.0001

Data Index: 1343727 (C4 (Web Text))

Max Activating Token Index: 57