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

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

Neuron 3178 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.7001. Min Act: -0.0001

Data Index: 404818 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.6282. Min Act: -0.0001

Data Index: 1239183 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.3727. Min Act: -0.0001

Data Index: 337826 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.3466. Min Act: -0.0001

Data Index: 906485 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.2988. Min Act: -0.0001

Data Index: 897356 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.4007. Min Act: -0.0001

Data Index: 744406 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.0753. Min Act: -0.0001

Data Index: 202911 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.2227. Min Act: -0.0001

Data Index: 1044533 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 3.7001. Min Range: -3.7001

Max Act: 2.9404. Min Act: -0.0001

Data Index: 145866 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.0842. Min Act: -0.0001

Data Index: 1261125 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.0282. Min Act: -0.0001

Data Index: 781477 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 3.7001. Min Range: -3.7001

Max Act: 2.9776. Min Act: -0.0001

Data Index: 937070 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 3.7001. Min Range: -3.7001

Max Act: 2.9805. Min Act: -0.0001

Data Index: 86623 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 3.7001. Min Range: -3.7001

Max Act: 2.8406. Min Act: -0.0001

Data Index: 542966 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 3.7001. Min Range: -3.7001

Max Act: 2.8240. Min Act: -0.0001

Data Index: 626080 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 3.7001. Min Range: -3.7001

Max Act: 2.9491. Min Act: -0.0001

Data Index: 51026 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 3.7001. Min Range: -3.7001

Max Act: 2.8200. Min Act: -0.0001

Data Index: 1129062 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 3.7001. Min Range: -3.7001

Max Act: 2.9492. Min Act: -0.0001

Data Index: 1120775 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 3.7001. Min Range: -3.7001

Max Act: 2.9290. Min Act: -0.0001

Data Index: 955483 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 3.7001. Min Range: -3.7001

Max Act: 2.9284. Min Act: -0.0001

Data Index: 512921 (C4 (Web Text))

Max Activating Token Index: 997