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

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

Neuron 1891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.2969. Min Act: -0.0000

Data Index: 1342353 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.7147. Min Act: -0.0000

Data Index: 47848 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.4166. Min Act: -0.0000

Data Index: 1024386 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.3646. Min Act: -0.0000

Data Index: 367928 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.1393. Min Act: -0.0000

Data Index: 718417 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.3126. Min Act: -0.0000

Data Index: 614644 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.0269. Min Act: -0.0000

Data Index: 40173 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.9981. Min Act: -0.0000

Data Index: 589485 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.9814. Min Act: -0.0000

Data Index: 464725 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.8976. Min Act: -0.0000

Data Index: 1608301 (Python Code)

Max Activating Token Index: 244

Text #10

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.8141. Min Act: -0.0000

Data Index: 59051 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.8711. Min Act: -0.0000

Data Index: 1186156 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.8524. Min Act: -0.0000

Data Index: 782958 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.0584. Min Act: -0.0000

Data Index: 1117489 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.9465. Min Act: -0.0000

Data Index: 1165836 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.8500. Min Act: -0.0000

Data Index: 365341 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.8305. Min Act: -0.0000

Data Index: 455080 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.8059. Min Act: -0.0000

Data Index: 1150222 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.8098. Min Act: -0.0000

Data Index: 188832 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 2.7147. Min Range: -2.7147

Max Act: 1.7719. Min Act: -0.0000

Data Index: 870718 (C4 (Web Text))

Max Activating Token Index: 146