Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3042 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1573072 (Python Code)

Max Activating Token Index: 571

Text #1

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1653562 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0003

Data Index: 30770 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0003

Data Index: 714337 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 531494 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1540932 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 671344 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1407028 (Python Code)

Max Activating Token Index: 36

Text #8

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 679106 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 80600 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1002804 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 36263 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 715351 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0004

Data Index: 50511 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1652109 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0033. Min Act: -0.0003

Data Index: 229655 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1454492 (Python Code)

Max Activating Token Index: 377

Text #17

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1438128 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 268688 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0033. Min Act: -0.0003

Data Index: 659319 (C4 (Web Text))

Max Activating Token Index: 526