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

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

Neuron 5889 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2303. Min Range: -4.2303

Max Act: 4.0118. Min Act: -0.0000

Data Index: 721685 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 4.2303. Min Range: -4.2303

Max Act: 4.2303. Min Act: -0.0000

Data Index: 970774 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 4.2303. Min Range: -4.2303

Max Act: 3.7203. Min Act: -0.0000

Data Index: 853391 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 4.2303. Min Range: -4.2303

Max Act: 3.2676. Min Act: -0.0000

Data Index: 228767 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 4.2303. Min Range: -4.2303

Max Act: 3.1237. Min Act: -0.0000

Data Index: 544390 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 4.2303. Min Range: -4.2303

Max Act: 3.3136. Min Act: -0.0000

Data Index: 4683 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 4.2303. Min Range: -4.2303

Max Act: 3.2924. Min Act: -0.0000

Data Index: 1109415 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 4.2303. Min Range: -4.2303

Max Act: 3.1502. Min Act: -0.0000

Data Index: 68462 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 4.2303. Min Range: -4.2303

Max Act: 3.1287. Min Act: -0.0000

Data Index: 1145449 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 4.2303. Min Range: -4.2303

Max Act: 3.1105. Min Act: -0.0000

Data Index: 370296 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 4.2303. Min Range: -4.2303

Max Act: 2.9863. Min Act: -0.0000

Data Index: 1073376 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 4.2303. Min Range: -4.2303

Max Act: 3.0048. Min Act: -0.0000

Data Index: 1245976 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 4.2303. Min Range: -4.2303

Max Act: 2.8594. Min Act: -0.0000

Data Index: 131163 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 4.2303. Min Range: -4.2303

Max Act: 2.8133. Min Act: -0.0000

Data Index: 1052883 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 4.2303. Min Range: -4.2303

Max Act: 2.8410. Min Act: -0.0000

Data Index: 360933 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 4.2303. Min Range: -4.2303

Max Act: 2.9678. Min Act: -0.0000

Data Index: 799793 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 4.2303. Min Range: -4.2303

Max Act: 2.7895. Min Act: -0.0000

Data Index: 1117225 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 4.2303. Min Range: -4.2303

Max Act: 2.9740. Min Act: -0.0000

Data Index: 755226 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 4.2303. Min Range: -4.2303

Max Act: 2.9489. Min Act: -0.0000

Data Index: 291299 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 4.2303. Min Range: -4.2303

Max Act: 2.9332. Min Act: -0.0000

Data Index: 1416822 (Python Code)

Max Activating Token Index: 89