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

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

Neuron 2639 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5672. Min Range: -1.5672

Max Act: 1.4958. Min Act: -0.0000

Data Index: 982535 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 1.5672. Min Range: -1.5672

Max Act: 1.5672. Min Act: -0.0000

Data Index: 392697 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 1.5672. Min Range: -1.5672

Max Act: 1.3934. Min Act: -0.0000

Data Index: 761925 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.7069. Min Act: -0.0000

Data Index: 270733 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.8871. Min Act: -0.0000

Data Index: 194139 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1115567 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1000250 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.8349. Min Act: -0.0000

Data Index: 639942 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.8390. Min Act: -0.0000

Data Index: 58938 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.8739. Min Act: -0.0000

Data Index: 626520 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.7580. Min Act: -0.0000

Data Index: 641189 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1274144 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.8447. Min Act: -0.0000

Data Index: 574110 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.7897. Min Act: -0.0000

Data Index: 144957 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.7908. Min Act: -0.0000

Data Index: 67396 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1004931 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.7703. Min Act: -0.0000

Data Index: 586706 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.7215. Min Act: -0.0000

Data Index: 988954 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1133993 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.5672. Min Range: -1.5672

Max Act: 0.6998. Min Act: -0.0000

Data Index: 138724 (C4 (Web Text))

Max Activating Token Index: 985