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

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

Neuron 3322 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: 0.6649. Min Range: -0.6649

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1236321 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6491. Min Act: -0.0000

Data Index: 312160 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6358. Min Act: -0.0000

Data Index: 474275 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5868. Min Act: -0.0001

Data Index: 1106986 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6362. Min Act: -0.0001

Data Index: 569267 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6067. Min Act: -0.0001

Data Index: 410599 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6292. Min Act: -0.0001

Data Index: 874974 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6124. Min Act: -0.0001

Data Index: 11072 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5863. Min Act: -0.0001

Data Index: 381025 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5402. Min Act: -0.0001

Data Index: 392818 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5519. Min Act: -0.0000

Data Index: 780234 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4897. Min Act: -0.0001

Data Index: 1397450 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4838. Min Act: -0.0001

Data Index: 1317874 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4665. Min Act: -0.0001

Data Index: 1617584 (Python Code)

Max Activating Token Index: 497

Text #14

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5076. Min Act: -0.0001

Data Index: 241637 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5217. Min Act: -0.0000

Data Index: 475878 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5321. Min Act: -0.0001

Data Index: 856484 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4793. Min Act: -0.0001

Data Index: 437931 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.4819. Min Act: -0.0001

Data Index: 881315 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5087. Min Act: -0.0000

Data Index: 811570 (C4 (Web Text))

Max Activating Token Index: 21