Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1769 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4636. Min Act: -0.0004

Data Index: 1264577 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4419. Min Act: -0.0004

Data Index: 168026 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3924. Min Act: -0.0004

Data Index: 316109 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3729. Min Act: -0.0004

Data Index: 1253593 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4113. Min Act: -0.0004

Data Index: 1035408 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3957. Min Act: -0.0004

Data Index: 763017 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4077. Min Act: -0.0004

Data Index: 779065 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3872. Min Act: -0.0004

Data Index: 717248 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3859. Min Act: -0.0004

Data Index: 1351979 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3845. Min Act: -0.0004

Data Index: 667673 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3592. Min Act: -0.0004

Data Index: 413367 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3700. Min Act: -0.0004

Data Index: 120750 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3671. Min Act: -0.0004

Data Index: 397289 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3406. Min Act: -0.0004

Data Index: 89241 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3845. Min Act: -0.0004

Data Index: 3400 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3577. Min Act: -0.0004

Data Index: 624457 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3693. Min Act: -0.0004

Data Index: 1166120 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3426. Min Act: -0.0004

Data Index: 342961 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3945. Min Act: -0.0004

Data Index: 873876 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3374. Min Act: -0.0004

Data Index: 1258526 (C4 (Web Text))

Max Activating Token Index: 284