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

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

Neuron 3615 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: 4.3762. Min Range: -4.3762

Max Act: 4.3762. Min Act: -0.0000

Data Index: 835101 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.7835. Min Act: -0.0000

Data Index: 812777 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.9214. Min Act: -0.0000

Data Index: 1227794 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.7228. Min Act: -0.0000

Data Index: 1026509 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.8747. Min Act: -0.0000

Data Index: 196549 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.6715. Min Act: -0.0000

Data Index: 1331577 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.5069. Min Act: -0.0000

Data Index: 105287 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.4517. Min Act: -0.0000

Data Index: 558072 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.4567. Min Act: -0.0000

Data Index: 1153731 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.4641. Min Act: -0.0000

Data Index: 866978 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.4469. Min Act: -0.0000

Data Index: 1344676 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.5605. Min Act: -0.0000

Data Index: 27285 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.4044. Min Act: -0.0000

Data Index: 588768 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.5536. Min Act: -0.0000

Data Index: 1050283 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.5286. Min Act: -0.0000

Data Index: 1226993 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.3549. Min Act: -0.0000

Data Index: 843846 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.4979. Min Act: -0.0000

Data Index: 381933 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.6628. Min Act: -0.0000

Data Index: 945356 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.3350. Min Act: -0.0000

Data Index: 379371 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 4.3762. Min Range: -4.3762

Max Act: 3.6176. Min Act: -0.0000

Data Index: 439414 (C4 (Web Text))

Max Activating Token Index: 226