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

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

Neuron 508 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3998. Min Range: -1.3998

Max Act: 1.3998. Min Act: -0.0000

Data Index: 1530533 (Python Code)

Max Activating Token Index: 281

Text #1

Max Range: 1.3998. Min Range: -1.3998

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1496659 (Python Code)

Max Activating Token Index: 466

Text #2

Max Range: 1.3998. Min Range: -1.3998

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1379492 (Python Code)

Max Activating Token Index: 429

Text #3

Max Range: 1.3998. Min Range: -1.3998

Max Act: 1.0226. Min Act: -0.0000

Data Index: 1513926 (Python Code)

Max Activating Token Index: 692

Text #4

Max Range: 1.3998. Min Range: -1.3998

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1509908 (Python Code)

Max Activating Token Index: 285

Text #5

Max Range: 1.3998. Min Range: -1.3998

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1595543 (Python Code)

Max Activating Token Index: 746

Text #6

Max Range: 1.3998. Min Range: -1.3998

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1481693 (Python Code)

Max Activating Token Index: 538

Text #7

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1424575 (Python Code)

Max Activating Token Index: 74

Text #8

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.9691. Min Act: -0.0000

Data Index: 981977 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.3998. Min Range: -1.3998

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1606932 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1575129 (Python Code)

Max Activating Token Index: 198

Text #11

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1612786 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 1.3998. Min Range: -1.3998

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1647685 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.9789. Min Act: -0.0000

Data Index: 947659 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.9074. Min Act: -0.0000

Data Index: 100437 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1509950 (Python Code)

Max Activating Token Index: 501

Text #16

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.8553. Min Act: -0.0000

Data Index: 956235 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1465072 (Python Code)

Max Activating Token Index: 142

Text #18

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.8673. Min Act: -0.0000

Data Index: 101677 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 1.3998. Min Range: -1.3998

Max Act: 0.8534. Min Act: -0.0000

Data Index: 169882 (C4 (Web Text))

Max Activating Token Index: 252