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

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

Neuron 3109 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: 1.7730. Min Range: -1.7730

Max Act: 1.7730. Min Act: -0.0000

Data Index: 319028 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.5725. Min Act: -0.0000

Data Index: 752769 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.1566. Min Act: -0.0001

Data Index: 503875 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1116155 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.1761. Min Act: -0.0000

Data Index: 545041 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 1.7730. Min Range: -1.7730

Max Act: 1.2232. Min Act: -0.0000

Data Index: 432455 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.7614. Min Act: -0.0001

Data Index: 843776 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.6234. Min Act: -0.0001

Data Index: 1545665 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5780. Min Act: -0.0001

Data Index: 1366222 (Python Code)

Max Activating Token Index: 552

Text #9

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.6170. Min Act: -0.0001

Data Index: 438476 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5741. Min Act: -0.0000

Data Index: 641741 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5485. Min Act: -0.0001

Data Index: 359827 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5366. Min Act: -0.0001

Data Index: 1139279 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5390. Min Act: -0.0001

Data Index: 1122059 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5187. Min Act: -0.0001

Data Index: 598996 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5553. Min Act: -0.0001

Data Index: 718346 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5502. Min Act: -0.0000

Data Index: 413165 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1572437 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5676. Min Act: -0.0001

Data Index: 1584403 (Python Code)

Max Activating Token Index: 178

Text #19

Max Range: 1.7730. Min Range: -1.7730

Max Act: 0.5387. Min Act: -0.0001

Data Index: 1384407 (Python Code)

Max Activating Token Index: 788