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

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

Neuron 534 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0545. Min Range: -1.0545

Max Act: 1.0545. Min Act: -0.0000

Data Index: 337062 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8536. Min Act: -0.0000

Data Index: 803009 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1106152 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1016536 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1339795 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1512185 (Python Code)

Max Activating Token Index: 705

Text #6

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.5036. Min Act: -0.0000

Data Index: 591756 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1065224 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1351892 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1342122 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.4828. Min Act: -0.0000

Data Index: 701670 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.5337. Min Act: -0.0000

Data Index: 216980 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1035100 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.4635. Min Act: -0.0000

Data Index: 596888 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.3999. Min Act: -0.0000

Data Index: 671537 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.4287. Min Act: -0.0000

Data Index: 489384 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1177380 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1309227 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.4386. Min Act: -0.0000

Data Index: 702529 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.4471. Min Act: -0.0000

Data Index: 52118 (C4 (Web Text))

Max Activating Token Index: 102