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

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

Neuron 2369 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.5391. Min Act: -0.0000

Data Index: 646657 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4373. Min Act: -0.0000

Data Index: 882334 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4391. Min Act: 0.0000

Data Index: 565945 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3736. Min Act: -0.0000

Data Index: 970148 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2837. Min Act: -0.0000

Data Index: 677932 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1568766 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2830. Min Act: -0.0000

Data Index: 220749 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3022. Min Act: -0.0000

Data Index: 692797 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2867. Min Act: -0.0000

Data Index: 362648 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1402558 (Python Code)

Max Activating Token Index: 877

Text #10

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1468192 (Python Code)

Max Activating Token Index: 434

Text #11

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2625. Min Act: -0.0000

Data Index: 218438 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1442778 (Python Code)

Max Activating Token Index: 150

Text #13

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1646275 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1406594 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2227. Min Act: -0.0000

Data Index: 360209 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2318. Min Act: -0.0000

Data Index: 318915 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1377688 (Python Code)

Max Activating Token Index: 310

Text #18

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1651904 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.2249. Min Act: -0.0000

Data Index: 1480289 (Python Code)

Max Activating Token Index: 957