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

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

Neuron 3660 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6463. Min Act: -0.0000

Data Index: 974107 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6452. Min Act: -0.0000

Data Index: 944495 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6666. Min Act: -0.0000

Data Index: 350355 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5816. Min Act: -0.0000

Data Index: 425596 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6277. Min Act: -0.0000

Data Index: 334449 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6635. Min Act: -0.0000

Data Index: 430219 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1318458 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1047674 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1320054 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5692. Min Act: -0.0000

Data Index: 876148 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6216. Min Act: -0.0000

Data Index: 400549 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1311099 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1255826 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1118116 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5947. Min Act: -0.0000

Data Index: 722416 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5455. Min Act: -0.0000

Data Index: 597145 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1445847 (Python Code)

Max Activating Token Index: 93

Text #17

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5792. Min Act: -0.0000

Data Index: 434736 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5283. Min Act: -0.0000

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5984. Min Act: -0.0000

Data Index: 876485 (C4 (Web Text))

Max Activating Token Index: 779