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

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

Neuron 808 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7996. Min Act: -0.0001

Data Index: 664732 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7809. Min Act: -0.0001

Data Index: 134407 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7791. Min Act: -0.0001

Data Index: 73888 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7948. Min Act: -0.0001

Data Index: 535634 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7544. Min Act: -0.0001

Data Index: 667726 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7691. Min Act: -0.0001

Data Index: 802604 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7373. Min Act: -0.0001

Data Index: 943428 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6858. Min Act: -0.0001

Data Index: 1247760 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7311. Min Act: -0.0001

Data Index: 513643 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7288. Min Act: -0.0001

Data Index: 284254 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7261. Min Act: -0.0001

Data Index: 536266 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7261. Min Act: -0.0001

Data Index: 72509 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7218. Min Act: -0.0001

Data Index: 439931 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7049. Min Act: -0.0001

Data Index: 187301 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6832. Min Act: -0.0001

Data Index: 995284 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7005. Min Act: -0.0001

Data Index: 703386 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7032. Min Act: -0.0001

Data Index: 586916 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6971. Min Act: -0.0001

Data Index: 1301236 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6768. Min Act: -0.0001

Data Index: 481642 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7202. Min Act: -0.0001

Data Index: 334141 (C4 (Web Text))

Max Activating Token Index: 936