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

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

Neuron 1329 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.6142. Min Act: -0.0002

Data Index: 498324 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5838. Min Act: -0.0001

Data Index: 4377 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5999. Min Act: -0.0002

Data Index: 644912 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5770. Min Act: -0.0002

Data Index: 243101 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5178. Min Act: -0.0001

Data Index: 765644 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5538. Min Act: -0.0001

Data Index: 1108715 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5405. Min Act: -0.0002

Data Index: 32853 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5379. Min Act: -0.0001

Data Index: 576208 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5354. Min Act: -0.0002

Data Index: 569167 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5854. Min Act: -0.0001

Data Index: 52807 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5113. Min Act: -0.0002

Data Index: 14009 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5121. Min Act: -0.0002

Data Index: 1289940 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.4891. Min Act: -0.0002

Data Index: 1269649 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5017. Min Act: -0.0001

Data Index: 1233324 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.5074. Min Act: -0.0001

Data Index: 801635 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.3968. Min Act: -0.0002

Data Index: 163989 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.3787. Min Act: -0.0001

Data Index: 1631323 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.3424. Min Act: -0.0001

Data Index: 1297589 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.3388. Min Act: -0.0002

Data Index: 428819 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.6142. Min Range: -0.6142

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1618054 (Python Code)

Max Activating Token Index: 37