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

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

Neuron 677 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.7727. Min Act: -0.0001

Data Index: 223812 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5829. Min Act: -0.0001

Data Index: 640077 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1288064 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5533. Min Act: -0.0000

Data Index: 924160 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5009. Min Act: -0.0000

Data Index: 401518 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4636. Min Act: -0.0000

Data Index: 430061 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1039831 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4700. Min Act: -0.0001

Data Index: 445085 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1080256 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4548. Min Act: -0.0000

Data Index: 15666 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4692. Min Act: -0.0000

Data Index: 951406 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4644. Min Act: -0.0000

Data Index: 72762 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4332. Min Act: -0.0000

Data Index: 632308 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4389. Min Act: -0.0001

Data Index: 274166 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4104. Min Act: -0.0000

Data Index: 61372 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4520. Min Act: -0.0000

Data Index: 414806 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4351. Min Act: -0.0000

Data Index: 170371 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4476. Min Act: -0.0001

Data Index: 619048 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4039. Min Act: -0.0001

Data Index: 76388 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.4397. Min Act: -0.0000

Data Index: 242368 (C4 (Web Text))

Max Activating Token Index: 603