Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1818 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.3940. Min Act: -0.0000

Data Index: 328402 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.3899. Min Act: -0.0000

Data Index: 699778 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.3476. Min Act: -0.0000

Data Index: 860963 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2697. Min Act: -0.0000

Data Index: 272601 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1048193 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.1650. Min Act: -0.0000

Data Index: 412053 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.1372. Min Act: -0.0000

Data Index: 446257 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.9833. Min Act: -0.0000

Data Index: 296758 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.8776. Min Act: -0.0000

Data Index: 467142 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1319412 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.9230. Min Act: -0.0000

Data Index: 427459 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.9389. Min Act: -0.0000

Data Index: 974004 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.8992. Min Act: -0.0000

Data Index: 728850 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.8521. Min Act: 0.0000

Data Index: 564450 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1320332 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.8355. Min Act: -0.0000

Data Index: 94675 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.8600. Min Act: -0.0000

Data Index: 115835 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.9191. Min Act: -0.0000

Data Index: 362487 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.8285. Min Act: -0.0000

Data Index: 689680 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.3940. Min Range: -1.3940

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1052085 (C4 (Web Text))

Max Activating Token Index: 50