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

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

Neuron 3594 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: 4.1823. Min Range: -4.1823

Max Act: 4.0592. Min Act: -0.0000

Data Index: 1257571 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.0579. Min Act: -0.0000

Data Index: 598709 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 4.1823. Min Range: -4.1823

Max Act: 4.1823. Min Act: -0.0000

Data Index: 861593 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.7345. Min Act: -0.0000

Data Index: 1294180 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.6032. Min Act: -0.0000

Data Index: 1048340 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.8626. Min Act: -0.0000

Data Index: 641169 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.6917. Min Act: -0.0000

Data Index: 1325245 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.5596. Min Act: -0.0000

Data Index: 622334 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.4610. Min Act: -0.0000

Data Index: 49985 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.5699. Min Act: -0.0000

Data Index: 1351329 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.2739. Min Act: -0.0000

Data Index: 669595 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.2720. Min Act: -0.0000

Data Index: 979145 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.1115. Min Act: -0.0000

Data Index: 1305329 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.2626. Min Act: -0.0000

Data Index: 62744 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.4180. Min Act: -0.0000

Data Index: 578240 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.3940. Min Act: -0.0000

Data Index: 1144307 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.5205. Min Act: -0.0000

Data Index: 385432 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.3635. Min Act: -0.0000

Data Index: 1039481 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.6348. Min Act: -0.0000

Data Index: 1108560 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 4.1823. Min Range: -4.1823

Max Act: 3.3182. Min Act: -0.0000

Data Index: 406870 (C4 (Web Text))

Max Activating Token Index: 292