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

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

Neuron 2565 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.4290. Min Act: -0.0002

Data Index: 780523 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3941. Min Act: -0.0002

Data Index: 812948 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3680. Min Act: -0.0002

Data Index: 22201 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.4167. Min Act: -0.0002

Data Index: 742493 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3581. Min Act: -0.0002

Data Index: 139388 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3086. Min Act: -0.0002

Data Index: 1038265 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3664. Min Act: -0.0002

Data Index: 160054 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3135. Min Act: -0.0002

Data Index: 570135 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.2826. Min Act: -0.0002

Data Index: 290633 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3179. Min Act: -0.0002

Data Index: 768289 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3133. Min Act: -0.0002

Data Index: 956017 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3017. Min Act: -0.0002

Data Index: 1122574 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3018. Min Act: -0.0002

Data Index: 537688 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.2683. Min Act: -0.0002

Data Index: 1011303 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3277. Min Act: -0.0002

Data Index: 680936 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.2802. Min Act: -0.0002

Data Index: 1235840 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.2593. Min Act: -0.0002

Data Index: 963287 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.2537. Min Act: -0.0002

Data Index: 1056229 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.2990. Min Act: -0.0002

Data Index: 1352518 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 1.4290. Min Range: -1.4290

Max Act: 1.3042. Min Act: -0.0002

Data Index: 1301691 (C4 (Web Text))

Max Activating Token Index: 502