Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1923 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.9110. Min Act: -0.0002

Data Index: 1100584 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.9220. Min Act: -0.0001

Data Index: 855971 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.9078. Min Act: -0.0001

Data Index: 1020081 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.9507. Min Act: -0.0002

Data Index: 477681 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.8106. Min Act: -0.0002

Data Index: 792967 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.8214. Min Act: -0.0002

Data Index: 1011343 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7625. Min Act: -0.0001

Data Index: 691275 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7163. Min Act: -0.0002

Data Index: 1143257 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7525. Min Act: -0.0002

Data Index: 968666 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7316. Min Act: -0.0002

Data Index: 97093 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7775. Min Act: -0.0002

Data Index: 447716 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7363. Min Act: -0.0001

Data Index: 459038 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7711. Min Act: -0.0002

Data Index: 1294701 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.8251. Min Act: -0.0002

Data Index: 704869 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7799. Min Act: -0.0001

Data Index: 501373 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7794. Min Act: -0.0002

Data Index: 1122537 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7293. Min Act: -0.0002

Data Index: 118666 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.6815. Min Act: -0.0002

Data Index: 794318 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7469. Min Act: -0.0001

Data Index: 704340 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.9507. Min Range: -0.9507

Max Act: 0.7499. Min Act: -0.0002

Data Index: 697617 (C4 (Web Text))

Max Activating Token Index: 332