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

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

Neuron 259 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: 2.6900. Min Range: -2.6900

Max Act: 2.6900. Min Act: -0.0000

Data Index: 1381350 (Python Code)

Max Activating Token Index: 43

Text #1

Max Range: 2.6900. Min Range: -2.6900

Max Act: 2.2020. Min Act: -0.0000

Data Index: 133349 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.8815. Min Act: -0.0000

Data Index: 1460020 (Python Code)

Max Activating Token Index: 374

Text #3

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.9808. Min Act: -0.0000

Data Index: 1533551 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.9049. Min Act: -0.0000

Data Index: 1531366 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.9109. Min Act: -0.0000

Data Index: 871924 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.8550. Min Act: -0.0000

Data Index: 528457 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.8157. Min Act: -0.0000

Data Index: 496142 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.8024. Min Act: -0.0000

Data Index: 1651311 (Python Code)

Max Activating Token Index: 78

Text #9

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.7424. Min Act: -0.0000

Data Index: 1371345 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.7310. Min Act: -0.0000

Data Index: 595393 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.7258. Min Act: -0.0000

Data Index: 1550875 (Python Code)

Max Activating Token Index: 124

Text #12

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.7191. Min Act: -0.0000

Data Index: 838922 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.6152. Min Act: -0.0000

Data Index: 235328 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.6912. Min Act: -0.0000

Data Index: 718407 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.6855. Min Act: -0.0000

Data Index: 782624 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.6861. Min Act: -0.0000

Data Index: 1107002 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.7731. Min Act: -0.0000

Data Index: 1484083 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.5753. Min Act: -0.0000

Data Index: 1410042 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 2.6900. Min Range: -2.6900

Max Act: 1.6685. Min Act: -0.0000

Data Index: 1624788 (Python Code)

Max Activating Token Index: 577