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

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

Neuron 5787 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0935. Min Range: -1.0935

Max Act: 1.0935. Min Act: -0.0000

Data Index: 690766 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 1.0935. Min Range: -1.0935

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1350034 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1071909 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.8753. Min Act: -0.0000

Data Index: 914999 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7757. Min Act: -0.0000

Data Index: 818705 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7313. Min Act: -0.0000

Data Index: 729246 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1307173 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7480. Min Act: -0.0000

Data Index: 122197 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7415. Min Act: -0.0000

Data Index: 95779 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7301. Min Act: -0.0000

Data Index: 334881 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7486. Min Act: -0.0000

Data Index: 412809 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7066. Min Act: 0.0000

Data Index: 1216475 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7057. Min Act: -0.0000

Data Index: 120939 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.6969. Min Act: 0.0000

Data Index: 732590 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7039. Min Act: -0.0000

Data Index: 119661 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.6655. Min Act: -0.0000

Data Index: 498797 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.6262. Min Act: 0.0001

Data Index: 1109590 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1062594 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.6235. Min Act: -0.0000

Data Index: 271839 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1173676 (C4 (Web Text))

Max Activating Token Index: 321