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

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

Neuron 17 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8970. Min Act: -0.0001

Data Index: 1211947 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8874. Min Act: -0.0000

Data Index: 248124 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.9041. Min Act: -0.0001

Data Index: 989536 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1261711 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1233729 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8240. Min Act: -0.0001

Data Index: 1027923 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8182. Min Act: -0.0001

Data Index: 648811 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8398. Min Act: -0.0001

Data Index: 1230286 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7405. Min Act: -0.0001

Data Index: 1135145 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7859. Min Act: -0.0001

Data Index: 1256763 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7631. Min Act: -0.0001

Data Index: 874985 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7794. Min Act: -0.0001

Data Index: 776339 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8014. Min Act: -0.0001

Data Index: 741024 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7736. Min Act: -0.0001

Data Index: 761826 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7662. Min Act: -0.0001

Data Index: 390117 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7692. Min Act: -0.0001

Data Index: 1402345 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7587. Min Act: -0.0001

Data Index: 419316 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7086. Min Act: -0.0000

Data Index: 809780 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7516. Min Act: -0.0001

Data Index: 173224 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7279. Min Act: -0.0001

Data Index: 700483 (C4 (Web Text))

Max Activating Token Index: 431