Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3897 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.6194. Min Act: -0.0000

Data Index: 1080877 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.5588. Min Act: -0.0000

Data Index: 515279 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.5588. Min Act: -0.0000

Data Index: 1115938 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.4610. Min Act: -0.0000

Data Index: 1237631 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.4754. Min Act: -0.0000

Data Index: 646438 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.4322. Min Act: -0.0000

Data Index: 462403 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.4560. Min Act: -0.0000

Data Index: 542143 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.3132. Min Act: -0.0000

Data Index: 1285201 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.3315. Min Act: -0.0001

Data Index: 439975 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.3749. Min Act: -0.0000

Data Index: 118031 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.2037. Min Act: -0.0001

Data Index: 317701 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.3130. Min Act: -0.0000

Data Index: 1095309 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.3135. Min Act: -0.0001

Data Index: 1210194 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.2073. Min Act: -0.0000

Data Index: 1077525 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.4225. Min Act: -0.0000

Data Index: 214157 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.2980. Min Act: -0.0000

Data Index: 600382 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.1634. Min Act: -0.0000

Data Index: 1035783 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.3999. Min Act: -0.0000

Data Index: 266067 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.2593. Min Act: -0.0000

Data Index: 573303 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 2.6194. Min Range: -2.6194

Max Act: 2.3384. Min Act: -0.0000

Data Index: 334450 (C4 (Web Text))

Max Activating Token Index: 839