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

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

Neuron 2945 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.9064. Min Act: -0.0000

Data Index: 488498 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 5.1308. Min Range: -5.1308

Max Act: 5.1308. Min Act: -0.0000

Data Index: 148234 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.8041. Min Act: -0.0001

Data Index: 530538 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.6150. Min Act: -0.0001

Data Index: 98149 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.7344. Min Act: -0.0001

Data Index: 99294 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.7258. Min Act: -0.0001

Data Index: 754801 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.5482. Min Act: -0.0001

Data Index: 300808 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.6821. Min Act: -0.0001

Data Index: 333519 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.6577. Min Act: -0.0000

Data Index: 1307097 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.5693. Min Act: -0.0001

Data Index: 639802 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.7347. Min Act: -0.0001

Data Index: 1163546 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.8717. Min Act: -0.0001

Data Index: 1346434 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.4825. Min Act: -0.0001

Data Index: 993790 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.5694. Min Act: -0.0000

Data Index: 1105613 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.3753. Min Act: -0.0001

Data Index: 291216 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.4001. Min Act: -0.0000

Data Index: 397200 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.6135. Min Act: -0.0000

Data Index: 1232694 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.2298. Min Act: -0.0001

Data Index: 512499 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.1459. Min Act: -0.0001

Data Index: 925978 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 5.1308. Min Range: -5.1308

Max Act: 4.2965. Min Act: -0.0000

Data Index: 51462 (C4 (Web Text))

Max Activating Token Index: 635