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

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

Neuron 1492 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: 1.8965. Min Range: -1.8965

Max Act: 1.8965. Min Act: -0.0000

Data Index: 209939 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.8812. Min Act: -0.0001

Data Index: 393215 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.7196. Min Act: -0.0000

Data Index: 1202731 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.6977. Min Act: -0.0000

Data Index: 45155 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.6394. Min Act: -0.0000

Data Index: 427662 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.4891. Min Act: -0.0000

Data Index: 911901 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.3842. Min Act: -0.0000

Data Index: 1352746 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.4480. Min Act: -0.0000

Data Index: 355712 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.5140. Min Act: -0.0000

Data Index: 23544 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.4631. Min Act: -0.0000

Data Index: 507050 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.3620. Min Act: -0.0001

Data Index: 582315 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.3236. Min Act: -0.0000

Data Index: 877773 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.3597. Min Act: -0.0000

Data Index: 206881 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.2848. Min Act: -0.0000

Data Index: 1165235 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.4292. Min Act: -0.0000

Data Index: 409052 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.2860. Min Act: -0.0000

Data Index: 245999 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.2313. Min Act: -0.0000

Data Index: 737804 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.2907. Min Act: -0.0000

Data Index: 945901 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.1902. Min Act: -0.0000

Data Index: 953506 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 1.8965. Min Range: -1.8965

Max Act: 1.2210. Min Act: -0.0000

Data Index: 831175 (C4 (Web Text))

Max Activating Token Index: 470