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

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

Neuron 897 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: 0.4820. Min Range: -0.4820

Max Act: 0.4783. Min Act: -0.0000

Data Index: 882230 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4713. Min Act: -0.0000

Data Index: 56792 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1062176 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4820. Min Act: -0.0001

Data Index: 537421 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4213. Min Act: -0.0001

Data Index: 67573 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4231. Min Act: -0.0001

Data Index: 1332613 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1298613 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3915. Min Act: -0.0001

Data Index: 434221 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3531. Min Act: -0.0000

Data Index: 103870 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4078. Min Act: -0.0001

Data Index: 679571 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3720. Min Act: -0.0001

Data Index: 1142007 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3776. Min Act: -0.0000

Data Index: 626603 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4143. Min Act: -0.0001

Data Index: 598884 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3979. Min Act: -0.0001

Data Index: 662597 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3708. Min Act: -0.0001

Data Index: 798613 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3396. Min Act: -0.0001

Data Index: 149919 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3656. Min Act: -0.0001

Data Index: 242701 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3745. Min Act: -0.0000

Data Index: 427231 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4041. Min Act: -0.0001

Data Index: 183951 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3717. Min Act: -0.0000

Data Index: 368241 (C4 (Web Text))

Max Activating Token Index: 280