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

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

Neuron 1150 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.5159. Min Act: -0.0000

Data Index: 199727 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3980. Min Act: -0.0000

Data Index: 131973 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4346. Min Act: -0.0000

Data Index: 365956 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4619. Min Act: -0.0000

Data Index: 144716 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4674. Min Act: -0.0000

Data Index: 674040 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4364. Min Act: -0.0000

Data Index: 746033 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4335. Min Act: -0.0000

Data Index: 483561 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1194060 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4206. Min Act: -0.0000

Data Index: 160897 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1176602 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4101. Min Act: -0.0000

Data Index: 947185 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3779. Min Act: -0.0000

Data Index: 480916 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4142. Min Act: -0.0000

Data Index: 751282 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4116. Min Act: -0.0000

Data Index: 307981 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4364. Min Act: -0.0000

Data Index: 834405 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4229. Min Act: -0.0000

Data Index: 872393 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4350. Min Act: -0.0000

Data Index: 47550 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1002740 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1104536 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4036. Min Act: -0.0000

Data Index: 504660 (C4 (Web Text))

Max Activating Token Index: 663