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

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

Neuron 136 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.9643. Min Act: -0.0000

Data Index: 1267419 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.7402. Min Act: -0.0000

Data Index: 1057384 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.7515. Min Act: -0.0000

Data Index: 1619159 (Python Code)

Max Activating Token Index: 971

Text #3

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.8018. Min Act: -0.0000

Data Index: 727047 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.5943. Min Act: -0.0000

Data Index: 890696 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.6809. Min Act: -0.0000

Data Index: 1180210 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.5063. Min Act: -0.0000

Data Index: 991597 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.5839. Min Act: -0.0000

Data Index: 1128521 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.4802. Min Act: -0.0000

Data Index: 58147 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.5656. Min Act: -0.0000

Data Index: 1560874 (Python Code)

Max Activating Token Index: 305

Text #10

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.4156. Min Act: -0.0000

Data Index: 665666 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.3927. Min Act: -0.0000

Data Index: 600986 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1648034 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.4656. Min Act: -0.0000

Data Index: 269954 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.3588. Min Act: -0.0000

Data Index: 104342 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.3648. Min Act: -0.0000

Data Index: 1133034 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1243347 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.3469. Min Act: -0.0000

Data Index: 1296904 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.3457. Min Act: -0.0000

Data Index: 551816 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 1.9643. Min Range: -1.9643

Max Act: 1.3094. Min Act: -0.0000

Data Index: 910855 (C4 (Web Text))

Max Activating Token Index: 177