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

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

Neuron 3092 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.5531. Min Act: -0.0001

Data Index: 741075 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.3308. Min Act: -0.0001

Data Index: 78763 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.2815. Min Act: -0.0001

Data Index: 195863 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1188158 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.0538. Min Act: -0.0001

Data Index: 564197 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1220929 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.1503. Min Act: -0.0001

Data Index: 514130 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.5531. Min Range: -1.5531

Max Act: 1.0151. Min Act: -0.0000

Data Index: 595038 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.9801. Min Act: -0.0001

Data Index: 1513574 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.9713. Min Act: -0.0000

Data Index: 52068 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.9284. Min Act: -0.0000

Data Index: 732279 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.8853. Min Act: -0.0001

Data Index: 1191329 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.9130. Min Act: -0.0000

Data Index: 495936 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.8061. Min Act: -0.0001

Data Index: 1254684 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.8187. Min Act: -0.0000

Data Index: 44797 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.8174. Min Act: -0.0001

Data Index: 1026834 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.8211. Min Act: -0.0001

Data Index: 154976 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.7623. Min Act: -0.0001

Data Index: 281938 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.7557. Min Act: -0.0001

Data Index: 1229654 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 1.5531. Min Range: -1.5531

Max Act: 0.8137. Min Act: -0.0001

Data Index: 52709 (C4 (Web Text))

Max Activating Token Index: 447