Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1371 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5014. Min Act: -0.0003

Data Index: 482832 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4935. Min Act: -0.0004

Data Index: 467203 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4827. Min Act: -0.0003

Data Index: 227324 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4884. Min Act: -0.0003

Data Index: 1314671 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5042. Min Act: -0.0003

Data Index: 574700 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4802. Min Act: -0.0003

Data Index: 890009 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4891. Min Act: -0.0004

Data Index: 146580 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5162. Min Act: -0.0003

Data Index: 659524 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5107. Min Act: -0.0003

Data Index: 39064 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4633. Min Act: -0.0003

Data Index: 563442 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4303. Min Act: -0.0003

Data Index: 27637 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4686. Min Act: -0.0003

Data Index: 126815 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4448. Min Act: -0.0003

Data Index: 1135165 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4436. Min Act: -0.0003

Data Index: 249144 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4505. Min Act: -0.0003

Data Index: 1047707 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4373. Min Act: -0.0004

Data Index: 419808 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4525. Min Act: -0.0003

Data Index: 1133371 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4084. Min Act: -0.0004

Data Index: 1224474 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4496. Min Act: -0.0003

Data Index: 1043203 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4163. Min Act: -0.0003

Data Index: 692965 (C4 (Web Text))

Max Activating Token Index: 338