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

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

Neuron 4180 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: 0.3488. Min Range: -0.3488

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1234854 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3261. Min Act: -0.0000

Data Index: 678559 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3338. Min Act: -0.0000

Data Index: 200040 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3295. Min Act: -0.0000

Data Index: 52783 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3269. Min Act: -0.0000

Data Index: 92708 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1214928 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3051. Min Act: -0.0000

Data Index: 496307 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3110. Min Act: -0.0000

Data Index: 905091 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1292753 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2969. Min Act: -0.0000

Data Index: 232431 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1123148 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1312211 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2847. Min Act: -0.0000

Data Index: 120912 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2677. Min Act: -0.0000

Data Index: 439211 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2779. Min Act: -0.0000

Data Index: 63869 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2666. Min Act: -0.0000

Data Index: 382830 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2742. Min Act: -0.0000

Data Index: 623560 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2817. Min Act: -0.0000

Data Index: 957005 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2623. Min Act: -0.0000

Data Index: 469328 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1072147 (C4 (Web Text))

Max Activating Token Index: 163