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

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

Neuron 3150 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1172489 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.6383. Min Act: -0.0001

Data Index: 727229 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.6196. Min Act: -0.0001

Data Index: 680252 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.6163. Min Act: -0.0001

Data Index: 1120699 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1331196 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.6049. Min Act: -0.0001

Data Index: 538564 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5849. Min Act: -0.0001

Data Index: 1285416 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5834. Min Act: -0.0001

Data Index: 1194020 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5895. Min Act: -0.0000

Data Index: 730559 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.6017. Min Act: -0.0000

Data Index: 881812 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5975. Min Act: -0.0000

Data Index: 301502 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5785. Min Act: -0.0000

Data Index: 417107 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5621. Min Act: -0.0001

Data Index: 884715 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1297626 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5461. Min Act: -0.0000

Data Index: 560151 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5247. Min Act: -0.0000

Data Index: 56486 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5692. Min Act: -0.0000

Data Index: 888077 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5416. Min Act: -0.0000

Data Index: 520411 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5352. Min Act: -0.0000

Data Index: 629127 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1331668 (C4 (Web Text))

Max Activating Token Index: 707