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

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

Neuron 4707 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.9455. Min Act: -0.0000

Data Index: 1088104 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.6021. Min Act: -0.0000

Data Index: 449590 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.7201. Min Act: -0.0000

Data Index: 1114273 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.8073. Min Act: -0.0000

Data Index: 1293821 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.8132. Min Act: -0.0000

Data Index: 125952 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.9463. Min Act: -0.0000

Data Index: 1171725 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.6732. Min Act: -0.0000

Data Index: 1055696 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.4527. Min Act: -0.0000

Data Index: 1084517 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.2872. Min Act: -0.0000

Data Index: 1093018 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.4310. Min Act: -0.0000

Data Index: 546619 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.0733. Min Act: -0.0000

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.0772. Min Act: -0.0000

Data Index: 111635 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.4244. Min Act: -0.0000

Data Index: 1014577 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.2019. Min Act: -0.0000

Data Index: 445469 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.1863. Min Act: -0.0000

Data Index: 610841 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.0256. Min Act: -0.0000

Data Index: 327071 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 4.9463. Min Range: -4.9463

Max Act: 3.9986. Min Act: -0.0000

Data Index: 1091804 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 4.9463. Min Range: -4.9463

Max Act: 3.7957. Min Act: -0.0000

Data Index: 74247 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 4.9463. Min Range: -4.9463

Max Act: 3.9715. Min Act: -0.0000

Data Index: 1339392 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 4.9463. Min Range: -4.9463

Max Act: 4.1403. Min Act: -0.0000

Data Index: 336912 (C4 (Web Text))

Max Activating Token Index: 994