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

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

Neuron 3196 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1313928 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.7131. Min Act: -0.0000

Data Index: 441456 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6941. Min Act: -0.0000

Data Index: 339884 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1297589 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1290373 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.7526. Min Act: -0.0000

Data Index: 279647 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6861. Min Act: -0.0000

Data Index: 796495 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.7084. Min Act: -0.0000

Data Index: 310080 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1052544 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6615. Min Act: -0.0000

Data Index: 279193 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1346467 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6598. Min Act: -0.0000

Data Index: 859973 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6755. Min Act: -0.0000

Data Index: 44923 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6317. Min Act: -0.0000

Data Index: 65040 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1297753 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6560. Min Act: -0.0000

Data Index: 869237 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6471. Min Act: -0.0000

Data Index: 438040 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6900. Min Act: -0.0000

Data Index: 946172 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6679. Min Act: -0.0000

Data Index: 959675 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6949. Min Act: -0.0000

Data Index: 368457 (C4 (Web Text))

Max Activating Token Index: 322