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

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

Neuron 1071 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: 0.6626. Min Range: -0.6626

Max Act: 0.6626. Min Act: -0.0001

Data Index: 654606 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5807. Min Act: -0.0001

Data Index: 888763 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5535. Min Act: -0.0002

Data Index: 907470 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5222. Min Act: -0.0002

Data Index: 268760 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4922. Min Act: -0.0002

Data Index: 1287336 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5161. Min Act: -0.0001

Data Index: 160987 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5302. Min Act: -0.0001

Data Index: 503248 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.6175. Min Act: -0.0002

Data Index: 822043 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5013. Min Act: -0.0002

Data Index: 586418 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4291. Min Act: -0.0001

Data Index: 444336 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4643. Min Act: -0.0001

Data Index: 995255 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5321. Min Act: -0.0001

Data Index: 438411 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4628. Min Act: -0.0002

Data Index: 302651 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5317. Min Act: -0.0002

Data Index: 433708 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5031. Min Act: -0.0001

Data Index: 800835 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4966. Min Act: -0.0002

Data Index: 1048481 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4454. Min Act: -0.0002

Data Index: 389921 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5117. Min Act: -0.0002

Data Index: 682202 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.5456. Min Act: -0.0001

Data Index: 820454 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.6626. Min Range: -0.6626

Max Act: 0.4728. Min Act: -0.0001

Data Index: 126951 (C4 (Web Text))

Max Activating Token Index: 966