Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 580 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5029. Min Range: -1.5029

Max Act: 1.5029. Min Act: -0.0000

Data Index: 375788 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.5029. Min Range: -1.5029

Max Act: 1.2240. Min Act: -0.0000

Data Index: 1255081 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.5029. Min Range: -1.5029

Max Act: 1.1599. Min Act: -0.0000

Data Index: 382203 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 1.5029. Min Range: -1.5029

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1144513 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.5029. Min Range: -1.5029

Max Act: 1.1121. Min Act: -0.0000

Data Index: 992175 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 1.5029. Min Range: -1.5029

Max Act: 0.9953. Min Act: -0.0000

Data Index: 796087 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 1.5029. Min Range: -1.5029

Max Act: 1.0529. Min Act: -0.0000

Data Index: 705924 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 1.5029. Min Range: -1.5029

Max Act: 1.0016. Min Act: -0.0000

Data Index: 966441 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.5029. Min Range: -1.5029

Max Act: 0.9498. Min Act: -0.0000

Data Index: 441377 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 1.5029. Min Range: -1.5029

Max Act: 0.9852. Min Act: -0.0000

Data Index: 898162 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 1.5029. Min Range: -1.5029

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1123094 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 1.5029. Min Range: -1.5029

Max Act: 0.9337. Min Act: -0.0000

Data Index: 678005 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 1.5029. Min Range: -1.5029

Max Act: 0.9593. Min Act: -0.0000

Data Index: 99242 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 1.5029. Min Range: -1.5029

Max Act: 1.0156. Min Act: -0.0000

Data Index: 206989 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 1.5029. Min Range: -1.5029

Max Act: 0.8957. Min Act: -0.0000

Data Index: 483705 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.5029. Min Range: -1.5029

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1130025 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 1.5029. Min Range: -1.5029

Max Act: 0.9413. Min Act: -0.0000

Data Index: 328510 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 1.5029. Min Range: -1.5029

Max Act: 0.9348. Min Act: -0.0000

Data Index: 1165157 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 1.5029. Min Range: -1.5029

Max Act: 0.9310. Min Act: -0.0000

Data Index: 8286 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.5029. Min Range: -1.5029

Max Act: 0.8807. Min Act: -0.0000

Data Index: 374559 (C4 (Web Text))

Max Activating Token Index: 429