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

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

Neuron 3600 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.8910. Min Act: -0.0000

Data Index: 1185139 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 4.3046. Min Range: -4.3046

Max Act: 4.3046. Min Act: -0.0000

Data Index: 978902 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.7545. Min Act: -0.0000

Data Index: 18513 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 4.3046. Min Range: -4.3046

Max Act: 4.1055. Min Act: -0.0000

Data Index: 676271 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.9785. Min Act: -0.0000

Data Index: 1093218 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.7837. Min Act: -0.0000

Data Index: 92376 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.8989. Min Act: -0.0000

Data Index: 139674 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.7239. Min Act: -0.0000

Data Index: 435833 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.5867. Min Act: -0.0000

Data Index: 1243053 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.8200. Min Act: -0.0000

Data Index: 236167 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.5276. Min Act: -0.0000

Data Index: 1320706 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.5319. Min Act: -0.0000

Data Index: 773211 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.5306. Min Act: -0.0000

Data Index: 70497 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.6664. Min Act: -0.0000

Data Index: 351518 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.4673. Min Act: -0.0000

Data Index: 719026 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.4652. Min Act: -0.0000

Data Index: 217760 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.2807. Min Act: -0.0000

Data Index: 896477 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.4188. Min Act: -0.0000

Data Index: 1342009 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.4172. Min Act: -0.0000

Data Index: 164981 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 4.3046. Min Range: -4.3046

Max Act: 3.3715. Min Act: -0.0000

Data Index: 1042100 (C4 (Web Text))

Max Activating Token Index: 861