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

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

Neuron 1047 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: 1.5887. Min Range: -1.5887

Max Act: 1.5887. Min Act: -0.0000

Data Index: 138511 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.5798. Min Act: -0.0000

Data Index: 468083 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.5360. Min Act: -0.0000

Data Index: 1373002 (Python Code)

Max Activating Token Index: 95

Text #3

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.5215. Min Act: -0.0000

Data Index: 1338062 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.5372. Min Act: -0.0000

Data Index: 173235 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4773. Min Act: -0.0000

Data Index: 1350454 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3921. Min Act: -0.0000

Data Index: 416531 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4490. Min Act: -0.0000

Data Index: 122336 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4612. Min Act: -0.0000

Data Index: 1343118 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4225. Min Act: -0.0000

Data Index: 11196 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3319. Min Act: -0.0000

Data Index: 282066 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4117. Min Act: -0.0000

Data Index: 679562 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3974. Min Act: -0.0000

Data Index: 268395 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4058. Min Act: -0.0000

Data Index: 1325043 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1049291 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3990. Min Act: -0.0000

Data Index: 466302 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3635. Min Act: -0.0000

Data Index: 838837 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1083057 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3994. Min Act: -0.0000

Data Index: 984557 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3809. Min Act: -0.0000

Data Index: 407363 (C4 (Web Text))

Max Activating Token Index: 459