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

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

Neuron 568 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.5735. Min Act: -0.0000

Data Index: 925302 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.5310. Min Act: -0.0000

Data Index: 526328 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1202260 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1504245 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.5041. Min Act: -0.0000

Data Index: 51282 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4471. Min Act: -0.0000

Data Index: 135132 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4441. Min Act: -0.0000

Data Index: 685611 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4670. Min Act: -0.0000

Data Index: 493081 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1061648 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4539. Min Act: -0.0000

Data Index: 966075 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4420. Min Act: -0.0000

Data Index: 770806 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4228. Min Act: -0.0000

Data Index: 711529 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4276. Min Act: -0.0000

Data Index: 619429 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1043967 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1351768 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4136. Min Act: -0.0000

Data Index: 631569 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.3988. Min Act: -0.0000

Data Index: 183492 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4068. Min Act: -0.0000

Data Index: 288452 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1128468 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4033. Min Act: -0.0000

Data Index: 785062 (C4 (Web Text))

Max Activating Token Index: 459