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

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

Neuron 1414 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.4520. Min Act: -0.0002

Data Index: 986252 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3245. Min Act: -0.0003

Data Index: 348322 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2799. Min Act: -0.0002

Data Index: 124876 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2853. Min Act: -0.0002

Data Index: 716917 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2495. Min Act: -0.0002

Data Index: 653158 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2475. Min Act: -0.0002

Data Index: 195481 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2484. Min Act: -0.0002

Data Index: 619045 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2241. Min Act: -0.0002

Data Index: 193925 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2389. Min Act: -0.0002

Data Index: 595513 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2258. Min Act: -0.0002

Data Index: 827903 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2378. Min Act: -0.0002

Data Index: 88994 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1969. Min Act: -0.0002

Data Index: 378826 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2010. Min Act: -0.0002

Data Index: 662838 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2032. Min Act: -0.0002

Data Index: 699840 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2053. Min Act: -0.0002

Data Index: 419728 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2001. Min Act: -0.0002

Data Index: 1230697 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1982. Min Act: -0.0002

Data Index: 817129 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1709. Min Act: -0.0002

Data Index: 1160538 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1610. Min Act: -0.0002

Data Index: 112828 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1514. Min Act: -0.0002

Data Index: 194988 (C4 (Web Text))

Max Activating Token Index: 36