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

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

Neuron 340 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: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0000

Data Index: 109251 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0639. Min Act: -0.0000

Data Index: 412520 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1225113 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1151051 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1588957 (Python Code)

Max Activating Token Index: 219

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1355789 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0584. Min Act: -0.0000

Data Index: 144746 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0591. Min Act: -0.0000

Data Index: 534257 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0568. Min Act: -0.0000

Data Index: 343231 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1296566 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0568. Min Act: -0.0000

Data Index: 574100 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0546. Min Act: -0.0000

Data Index: 877051 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1387939 (Python Code)

Max Activating Token Index: 526

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1043793 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1101241 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0563. Min Act: -0.0000

Data Index: 174281 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1053993 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0555. Min Act: -0.0000

Data Index: 924622 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0588. Min Act: -0.0000

Data Index: 591494 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1444356 (Python Code)

Max Activating Token Index: 850