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

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

Neuron 3040 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.8217. Min Act: 0.0001

Data Index: 1021281 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1200117 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7120. Min Act: -0.0000

Data Index: 924364 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7202. Min Act: -0.0000

Data Index: 621886 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1255527 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4865. Min Act: 0.0000

Data Index: 961384 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4633. Min Act: -0.0000

Data Index: 471432 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4322. Min Act: -0.0000

Data Index: 22537 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4221. Min Act: -0.0000

Data Index: 434394 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4329. Min Act: -0.0000

Data Index: 540393 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1296602 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.3986. Min Act: -0.0000

Data Index: 369538 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1209433 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.3954. Min Act: 0.0000

Data Index: 1239964 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.3933. Min Act: -0.0000

Data Index: 642091 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.3870. Min Act: -0.0000

Data Index: 144493 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.3993. Min Act: -0.0000

Data Index: 281018 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.3993. Min Act: -0.0000

Data Index: 212081 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.3837. Min Act: 0.0000

Data Index: 6543 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.3959. Min Act: -0.0000

Data Index: 354399 (C4 (Web Text))

Max Activating Token Index: 657