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

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

Neuron 1545 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5966. Min Act: -0.0001

Data Index: 757978 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.6062. Min Act: -0.0001

Data Index: 755189 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.6098. Min Act: -0.0001

Data Index: 1331165 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5226. Min Act: -0.0001

Data Index: 1061970 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5443. Min Act: -0.0001

Data Index: 332553 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5723. Min Act: -0.0001

Data Index: 753795 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5334. Min Act: -0.0001

Data Index: 116258 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5940. Min Act: -0.0001

Data Index: 274197 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4912. Min Act: -0.0001

Data Index: 820858 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5174. Min Act: -0.0001

Data Index: 1383906 (Python Code)

Max Activating Token Index: 216

Text #10

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5133. Min Act: -0.0001

Data Index: 1351908 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5247. Min Act: -0.0001

Data Index: 657530 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5084. Min Act: -0.0001

Data Index: 435600 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5081. Min Act: -0.0001

Data Index: 944450 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5053. Min Act: -0.0001

Data Index: 56449 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5046. Min Act: -0.0001

Data Index: 464604 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5029. Min Act: -0.0001

Data Index: 1185890 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5048. Min Act: -0.0001

Data Index: 506360 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5036. Min Act: -0.0001

Data Index: 482767 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5014. Min Act: -0.0001

Data Index: 830771 (C4 (Web Text))

Max Activating Token Index: 161