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

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

Neuron 1052 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: 2.2456. Min Range: -2.2456

Max Act: 2.2456. Min Act: -0.0000

Data Index: 319204 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.9994. Min Act: -0.0001

Data Index: 1292684 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 2.2456. Min Range: -2.2456

Max Act: 2.0358. Min Act: -0.0000

Data Index: 46229 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 2.2456. Min Range: -2.2456

Max Act: 2.0122. Min Act: -0.0000

Data Index: 850786 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.9808. Min Act: -0.0000

Data Index: 75987 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.9716. Min Act: -0.0000

Data Index: 1069645 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.9341. Min Act: -0.0000

Data Index: 50254 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.7723. Min Act: -0.0000

Data Index: 1268378 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.8034. Min Act: -0.0001

Data Index: 194639 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.6860. Min Act: -0.0000

Data Index: 454352 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.8474. Min Act: -0.0000

Data Index: 402699 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.6409. Min Act: -0.0000

Data Index: 1073669 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.6904. Min Act: -0.0000

Data Index: 753901 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.5865. Min Act: -0.0000

Data Index: 143309 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.6615. Min Act: -0.0000

Data Index: 610077 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.6292. Min Act: -0.0001

Data Index: 918867 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.5312. Min Act: -0.0000

Data Index: 40604 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.6851. Min Act: -0.0000

Data Index: 608172 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.5013. Min Act: -0.0001

Data Index: 575508 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 2.2456. Min Range: -2.2456

Max Act: 1.5488. Min Act: -0.0001

Data Index: 750734 (C4 (Web Text))

Max Activating Token Index: 197