Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3391 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3739. Min Act: 0.0000

Data Index: 1272447 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3729. Min Act: -0.0000

Data Index: 741321 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3634. Min Act: -0.0000

Data Index: 479764 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1010180 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1224578 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3468. Min Act: -0.0000

Data Index: 843125 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3233. Min Act: -0.0000

Data Index: 107098 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1323628 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3221. Min Act: -0.0000

Data Index: 187748 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3113. Min Act: -0.0000

Data Index: 958305 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1155186 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3030. Min Act: -0.0000

Data Index: 160497 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1159797 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3135. Min Act: -0.0000

Data Index: 83637 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3106. Min Act: -0.0000

Data Index: 578654 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3149. Min Act: -0.0000

Data Index: 49919 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2920. Min Act: -0.0000

Data Index: 389715 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3103. Min Act: -0.0000

Data Index: 560252 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2906. Min Act: -0.0000

Data Index: 61583 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3110. Min Act: -0.0000

Data Index: 202600 (C4 (Web Text))

Max Activating Token Index: 888