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

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

Neuron 5944 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: 0.5977. Min Range: -0.5977

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1481176 (Python Code)

Max Activating Token Index: 1009

Text #1

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1603811 (Python Code)

Max Activating Token Index: 129

Text #2

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5823. Min Act: -0.0000

Data Index: 696494 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1387605 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1566428 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5496. Min Act: -0.0000

Data Index: 914855 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5553. Min Act: -0.0000

Data Index: 415048 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5347. Min Act: -0.0000

Data Index: 698224 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1246361 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1477549 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5248. Min Act: -0.0000

Data Index: 441707 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1372438 (Python Code)

Max Activating Token Index: 226

Text #12

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1620220 (Python Code)

Max Activating Token Index: 992

Text #13

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1597861 (Python Code)

Max Activating Token Index: 899

Text #14

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1466419 (Python Code)

Max Activating Token Index: 912

Text #15

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1400364 (Python Code)

Max Activating Token Index: 758

Text #16

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1506203 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1646918 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1558713 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1092151 (C4 (Web Text))

Max Activating Token Index: 879