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

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

Neuron 1795 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1463646 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1499620 (Python Code)

Max Activating Token Index: 889

Text #2

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3432. Min Act: -0.0000

Data Index: 612850 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1463514 (Python Code)

Max Activating Token Index: 939

Text #4

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1526304 (Python Code)

Max Activating Token Index: 442

Text #5

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1576221 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1373165 (Python Code)

Max Activating Token Index: 779

Text #7

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1476180 (Python Code)

Max Activating Token Index: 955

Text #8

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1510349 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1536224 (Python Code)

Max Activating Token Index: 131

Text #10

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1530714 (Python Code)

Max Activating Token Index: 883

Text #11

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1599004 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1422575 (Python Code)

Max Activating Token Index: 507

Text #13

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1414816 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1153377 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1428563 (Python Code)

Max Activating Token Index: 127

Text #16

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1624824 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1181616 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1553501 (Python Code)

Max Activating Token Index: 595

Text #19

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1519164 (Python Code)

Max Activating Token Index: 201