Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2544 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7937. Min Act: -0.0000

Data Index: 501871 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7157. Min Act: -0.0000

Data Index: 867187 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6724. Min Act: -0.0000

Data Index: 333918 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7120. Min Act: -0.0000

Data Index: 47201 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6727. Min Act: -0.0000

Data Index: 78966 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6431. Min Act: -0.0000

Data Index: 177019 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7491. Min Act: -0.0000

Data Index: 342719 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6485. Min Act: -0.0000

Data Index: 292658 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6330. Min Act: -0.0000

Data Index: 549425 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5901. Min Act: -0.0000

Data Index: 381607 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6025. Min Act: -0.0000

Data Index: 252984 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5857. Min Act: -0.0000

Data Index: 121017 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5847. Min Act: -0.0000

Data Index: 334267 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6080. Min Act: -0.0000

Data Index: 451390 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5810. Min Act: -0.0000

Data Index: 302216 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5627. Min Act: -0.0000

Data Index: 149892 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5815. Min Act: -0.0000

Data Index: 500951 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5687. Min Act: -0.0000

Data Index: 214104 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5863. Min Act: -0.0000

Data Index: 834639 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1218877 (C4 (Web Text))

Max Activating Token Index: 371