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

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

Neuron 3359 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.8314. Min Act: -0.0001

Data Index: 85495 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.8198. Min Act: -0.0001

Data Index: 312372 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7762. Min Act: -0.0001

Data Index: 242782 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7347. Min Act: -0.0002

Data Index: 110384 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7772. Min Act: -0.0001

Data Index: 259952 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7249. Min Act: -0.0001

Data Index: 465968 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7155. Min Act: -0.0001

Data Index: 181659 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7105. Min Act: -0.0001

Data Index: 276151 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6859. Min Act: -0.0002

Data Index: 198833 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6492. Min Act: -0.0001

Data Index: 910230 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7047. Min Act: -0.0001

Data Index: 931812 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7212. Min Act: -0.0001

Data Index: 1147306 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7229. Min Act: -0.0001

Data Index: 842618 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6709. Min Act: -0.0001

Data Index: 615934 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7270. Min Act: -0.0001

Data Index: 956309 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6835. Min Act: -0.0001

Data Index: 823274 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6309. Min Act: -0.0001

Data Index: 1274301 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6361. Min Act: -0.0001

Data Index: 481893 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6643. Min Act: -0.0001

Data Index: 1191230 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6883. Min Act: -0.0002

Data Index: 190890 (C4 (Web Text))

Max Activating Token Index: 313