Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3919 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.8154. Min Act: -0.0000

Data Index: 840170 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.3047. Min Act: -0.0000

Data Index: 1034511 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.4419. Min Act: -0.0000

Data Index: 18717 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.4219. Min Act: -0.0000

Data Index: 249751 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2700. Min Act: -0.0000

Data Index: 983804 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.3933. Min Act: -0.0000

Data Index: 889861 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.4943. Min Act: -0.0000

Data Index: 1065630 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2278. Min Act: -0.0000

Data Index: 1029611 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.1953. Min Act: -0.0000

Data Index: 343710 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2966. Min Act: -0.0000

Data Index: 1163484 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2782. Min Act: -0.0000

Data Index: 222834 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.1454. Min Act: -0.0000

Data Index: 1035903 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2449. Min Act: -0.0000

Data Index: 186905 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.1492. Min Act: -0.0000

Data Index: 986815 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.0413. Min Act: -0.0000

Data Index: 463273 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.1001. Min Act: -0.0000

Data Index: 285809 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.0998. Min Act: -0.0000

Data Index: 727269 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.0477. Min Act: -0.0000

Data Index: 161973 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.1463. Min Act: -0.0000

Data Index: 419081 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.9273. Min Act: -0.0000

Data Index: 356777 (C4 (Web Text))

Max Activating Token Index: 584