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

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

Neuron 3626 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.7198. Min Act: -0.0001

Data Index: 1208311 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4945. Min Act: -0.0000

Data Index: 859398 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4930. Min Act: -0.0000

Data Index: 667649 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4587. Min Act: -0.0000

Data Index: 515953 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4579. Min Act: -0.0000

Data Index: 572912 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4442. Min Act: -0.0000

Data Index: 560068 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4550. Min Act: -0.0000

Data Index: 499356 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1106089 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1051237 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1249637 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1277905 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1210015 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4315. Min Act: -0.0000

Data Index: 577056 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4139. Min Act: -0.0000

Data Index: 68840 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4018. Min Act: -0.0000

Data Index: 150925 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4006. Min Act: -0.0000

Data Index: 743675 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4118. Min Act: -0.0001

Data Index: 825747 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4129. Min Act: -0.0001

Data Index: 883183 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1206391 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1155916 (C4 (Web Text))

Max Activating Token Index: 399