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

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

Neuron 3897 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: 0.9442. Min Range: -0.9442

Max Act: 0.9442. Min Act: -0.0000

Data Index: 892383 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6910. Min Act: -0.0000

Data Index: 943859 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6598. Min Act: -0.0001

Data Index: 557261 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6263. Min Act: -0.0001

Data Index: 925409 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5459. Min Act: -0.0001

Data Index: 180084 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5773. Min Act: -0.0000

Data Index: 588844 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5719. Min Act: -0.0000

Data Index: 508991 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6065. Min Act: -0.0001

Data Index: 1326795 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5560. Min Act: -0.0000

Data Index: 504878 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5260. Min Act: -0.0001

Data Index: 1263355 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5350. Min Act: -0.0001

Data Index: 1202730 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5708. Min Act: -0.0000

Data Index: 436416 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1030148 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5131. Min Act: -0.0000

Data Index: 172596 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5080. Min Act: -0.0000

Data Index: 389007 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1343884 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.4970. Min Act: -0.0000

Data Index: 689969 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.4706. Min Act: -0.0001

Data Index: 1143985 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.4650. Min Act: -0.0001

Data Index: 931123 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.4633. Min Act: -0.0000

Data Index: 1111350 (C4 (Web Text))

Max Activating Token Index: 267