Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5490 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.5768. Min Act: -0.0001

Data Index: 907734 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.4816. Min Act: -0.0001

Data Index: 1253158 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.4011. Min Act: -0.0001

Data Index: 1224753 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3994. Min Act: -0.0001

Data Index: 997654 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3150. Min Act: -0.0001

Data Index: 521613 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3243. Min Act: -0.0001

Data Index: 686936 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3599. Min Act: -0.0001

Data Index: 1176905 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.2312. Min Act: -0.0001

Data Index: 117230 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.4315. Min Act: -0.0001

Data Index: 225023 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3368. Min Act: -0.0001

Data Index: 202657 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3058. Min Act: -0.0001

Data Index: 274543 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3563. Min Act: -0.0001

Data Index: 1236623 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3235. Min Act: -0.0001

Data Index: 1181366 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3825. Min Act: -0.0001

Data Index: 1011639 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.1865. Min Act: -0.0001

Data Index: 178621 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.2530. Min Act: -0.0001

Data Index: 1324843 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3350. Min Act: -0.0001

Data Index: 23354 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.5768. Min Range: -1.5768

Max Act: 0.7380. Min Act: -0.0001

Data Index: 806786 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.3315. Min Act: -0.0001

Data Index: 62603 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 1.5768. Min Range: -1.5768

Max Act: 1.1088. Min Act: -0.0001

Data Index: 1197448 (C4 (Web Text))

Max Activating Token Index: 232