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

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

Neuron 3275 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3873. Min Act: -0.0001

Data Index: 822723 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1119250 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3936. Min Act: -0.0001

Data Index: 926041 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3807. Min Act: -0.0001

Data Index: 1055000 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3540. Min Act: -0.0001

Data Index: 1324362 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3520. Min Act: -0.0001

Data Index: 290457 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3461. Min Act: -0.0001

Data Index: 126564 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3707. Min Act: -0.0001

Data Index: 924137 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3516. Min Act: -0.0001

Data Index: 1107379 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3135. Min Act: -0.0001

Data Index: 399819 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3465. Min Act: -0.0001

Data Index: 511733 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3404. Min Act: -0.0001

Data Index: 731353 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2735. Min Act: -0.0001

Data Index: 60751 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3118. Min Act: -0.0001

Data Index: 1224931 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3009. Min Act: -0.0001

Data Index: 479984 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2956. Min Act: -0.0001

Data Index: 677223 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2955. Min Act: -0.0001

Data Index: 515955 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2952. Min Act: -0.0001

Data Index: 1111551 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.3081. Min Act: -0.0001

Data Index: 194429 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.3936. Min Range: -0.3936

Max Act: 0.2800. Min Act: -0.0001

Data Index: 303289 (C4 (Web Text))

Max Activating Token Index: 370