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

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

Neuron 4436 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: 0.9925. Min Range: -0.9925

Max Act: 0.8720. Min Act: -0.0001

Data Index: 1079193 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.9074. Min Act: -0.0001

Data Index: 491911 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.9925. Min Act: -0.0001

Data Index: 1265709 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.9438. Min Act: -0.0001

Data Index: 399616 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.9393. Min Act: -0.0001

Data Index: 1090167 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8237. Min Act: -0.0001

Data Index: 328095 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7906. Min Act: -0.0001

Data Index: 1122166 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8452. Min Act: -0.0001

Data Index: 1054467 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8075. Min Act: -0.0001

Data Index: 110848 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8220. Min Act: -0.0001

Data Index: 751599 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8646. Min Act: -0.0001

Data Index: 1349638 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8477. Min Act: -0.0001

Data Index: 1188949 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.9277. Min Act: -0.0001

Data Index: 699221 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7816. Min Act: -0.0001

Data Index: 759654 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1634048 (Python Code)

Max Activating Token Index: 646

Text #15

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7862. Min Act: -0.0001

Data Index: 632965 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8054. Min Act: -0.0001

Data Index: 499088 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7785. Min Act: -0.0001

Data Index: 236416 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7836. Min Act: -0.0001

Data Index: 794939 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7998. Min Act: -0.0001

Data Index: 595629 (C4 (Web Text))

Max Activating Token Index: 95