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

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

Neuron 1000 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0563. Min Range: -1.0563

Max Act: 1.0563. Min Act: -0.0001

Data Index: 693539 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 1.0563. Min Range: -1.0563

Max Act: 1.0439. Min Act: -0.0000

Data Index: 166763 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1242631 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8979. Min Act: -0.0001

Data Index: 1001665 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.9206. Min Act: -0.0001

Data Index: 605674 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8880. Min Act: -0.0000

Data Index: 250902 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8732. Min Act: -0.0000

Data Index: 1168820 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8992. Min Act: -0.0000

Data Index: 457905 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8452. Min Act: -0.0001

Data Index: 1274766 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8960. Min Act: -0.0001

Data Index: 313963 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1005816 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1106912 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8933. Min Act: -0.0001

Data Index: 174747 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8346. Min Act: -0.0000

Data Index: 570158 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1269484 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1082487 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8170. Min Act: -0.0000

Data Index: 606910 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8051. Min Act: -0.0001

Data Index: 1308411 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1354465 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.7988. Min Act: -0.0001

Data Index: 774444 (C4 (Web Text))

Max Activating Token Index: 207