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

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

Neuron 2677 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: 1.5075. Min Range: -1.5075

Max Act: 1.5075. Min Act: -0.0002

Data Index: 462738 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.1745. Min Act: -0.0002

Data Index: 797431 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.9314. Min Act: -0.0002

Data Index: 765555 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.0170. Min Act: -0.0002

Data Index: 1043465 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.8545. Min Act: -0.0002

Data Index: 417675 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.8996. Min Act: -0.0001

Data Index: 277252 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.7392. Min Act: -0.0001

Data Index: 745194 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.7987. Min Act: -0.0002

Data Index: 734143 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.8757. Min Act: -0.0002

Data Index: 747695 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.8432. Min Act: -0.0001

Data Index: 818076 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.8847. Min Act: -0.0001

Data Index: 822789 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.7227. Min Act: -0.0002

Data Index: 1222192 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.7410. Min Act: -0.0002

Data Index: 664402 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.8005. Min Act: -0.0002

Data Index: 1040756 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.9719. Min Act: -0.0002

Data Index: 1309630 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.4891. Min Act: -0.0001

Data Index: 485947 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.7273. Min Act: -0.0001

Data Index: 1044965 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.8282. Min Act: -0.0002

Data Index: 791323 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.8460. Min Act: -0.0001

Data Index: 688337 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.7599. Min Act: -0.0002

Data Index: 510778 (C4 (Web Text))

Max Activating Token Index: 193