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

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

Neuron 3052 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.5571. Min Act: -0.0000

Data Index: 420728 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1251378 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4936. Min Act: -0.0000

Data Index: 583465 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1341886 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1647643 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4695. Min Act: -0.0000

Data Index: 516444 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1258845 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.5264. Min Act: -0.0000

Data Index: 101880 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1209778 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4613. Min Act: -0.0000

Data Index: 757654 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4578. Min Act: -0.0000

Data Index: 849229 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4418. Min Act: -0.0000

Data Index: 73210 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4398. Min Act: -0.0000

Data Index: 229125 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4552. Min Act: -0.0000

Data Index: 204828 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1099938 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3925. Min Act: -0.0000

Data Index: 931495 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1165070 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4055. Min Act: -0.0000

Data Index: 311934 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4146. Min Act: -0.0000

Data Index: 182762 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1103291 (C4 (Web Text))

Max Activating Token Index: 399