Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2761 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6904. Min Act: -0.0001

Data Index: 497428 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6288. Min Act: -0.0000

Data Index: 216527 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.7055. Min Act: -0.0001

Data Index: 110917 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5839. Min Act: -0.0000

Data Index: 825564 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5955. Min Act: -0.0001

Data Index: 883755 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6159. Min Act: -0.0001

Data Index: 1008832 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5868. Min Act: -0.0001

Data Index: 899051 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5481. Min Act: -0.0001

Data Index: 891728 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6486. Min Act: -0.0001

Data Index: 909914 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5681. Min Act: -0.0001

Data Index: 822074 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6325. Min Act: -0.0001

Data Index: 735903 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5886. Min Act: -0.0000

Data Index: 808417 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5890. Min Act: -0.0001

Data Index: 964046 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5689. Min Act: -0.0001

Data Index: 198504 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5309. Min Act: -0.0001

Data Index: 967545 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5418. Min Act: -0.0000

Data Index: 836332 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5885. Min Act: -0.0000

Data Index: 184432 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5631. Min Act: -0.0001

Data Index: 1194506 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5890. Min Act: -0.0001

Data Index: 1159901 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5476. Min Act: -0.0001

Data Index: 750133 (C4 (Web Text))

Max Activating Token Index: 533