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

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

Neuron 3274 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.9324. Min Act: -0.0000

Data Index: 1127444 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 5.4720. Min Range: -5.4720

Max Act: 5.4720. Min Act: -0.0001

Data Index: 332574 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 5.4720. Min Range: -5.4720

Max Act: 5.0450. Min Act: -0.0000

Data Index: 625882 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.3344. Min Act: -0.0000

Data Index: 733172 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.6822. Min Act: -0.0000

Data Index: 1290175 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.6352. Min Act: -0.0000

Data Index: 1340669 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.4357. Min Act: -0.0001

Data Index: 347683 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.1883. Min Act: -0.0001

Data Index: 1236595 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.1495. Min Act: -0.0001

Data Index: 642275 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.5857. Min Act: -0.0001

Data Index: 279283 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.2140. Min Act: -0.0000

Data Index: 85421 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.5375. Min Act: -0.0001

Data Index: 1157565 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 5.4720. Min Range: -5.4720

Max Act: 3.8735. Min Act: -0.0001

Data Index: 1250311 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.0223. Min Act: -0.0000

Data Index: 862939 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 5.4720. Min Range: -5.4720

Max Act: 3.9679. Min Act: -0.0000

Data Index: 675738 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 5.4720. Min Range: -5.4720

Max Act: 3.8173. Min Act: -0.0001

Data Index: 149339 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 5.4720. Min Range: -5.4720

Max Act: 4.0682. Min Act: -0.0001

Data Index: 789070 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 5.4720. Min Range: -5.4720

Max Act: 3.9923. Min Act: -0.0001

Data Index: 507550 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 5.4720. Min Range: -5.4720

Max Act: 3.8166. Min Act: -0.0001

Data Index: 779274 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 5.4720. Min Range: -5.4720

Max Act: 3.6438. Min Act: -0.0001

Data Index: 297830 (C4 (Web Text))

Max Activating Token Index: 951