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

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

Neuron 5586 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: 2.4900. Min Range: -2.4900

Max Act: 2.4900. Min Act: -0.0000

Data Index: 1324360 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.2717. Min Act: -0.0000

Data Index: 1212702 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.1340. Min Act: -0.0000

Data Index: 311070 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.2117. Min Act: -0.0000

Data Index: 524480 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.1964. Min Act: -0.0000

Data Index: 128073 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.1955. Min Act: -0.0000

Data Index: 194165 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.1959. Min Act: -0.0000

Data Index: 791779 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.1786. Min Act: -0.0000

Data Index: 239165 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.0664. Min Act: -0.0000

Data Index: 1515154 (Python Code)

Max Activating Token Index: 762

Text #9

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.0257. Min Act: -0.0000

Data Index: 1148987 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.0218. Min Act: -0.0000

Data Index: 454505 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 2.4900. Min Range: -2.4900

Max Act: 2.1308. Min Act: -0.0000

Data Index: 95946 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 2.4900. Min Range: -2.4900

Max Act: 1.8529. Min Act: -0.0000

Data Index: 830982 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 2.4900. Min Range: -2.4900

Max Act: 1.9061. Min Act: -0.0000

Data Index: 178734 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 2.4900. Min Range: -2.4900

Max Act: 1.8043. Min Act: -0.0000

Data Index: 1612507 (Python Code)

Max Activating Token Index: 79

Text #15

Max Range: 2.4900. Min Range: -2.4900

Max Act: 1.9028. Min Act: -0.0000

Data Index: 402671 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 2.4900. Min Range: -2.4900

Max Act: 1.9188. Min Act: -0.0000

Data Index: 1372352 (Python Code)

Max Activating Token Index: 844

Text #17

Max Range: 2.4900. Min Range: -2.4900

Max Act: 1.7189. Min Act: -0.0000

Data Index: 1595738 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 2.4900. Min Range: -2.4900

Max Act: 1.7013. Min Act: -0.0000

Data Index: 1230786 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 2.4900. Min Range: -2.4900

Max Act: 1.7925. Min Act: -0.0000

Data Index: 630684 (C4 (Web Text))

Max Activating Token Index: 598