Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3555 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.5503. Min Act: -0.0001

Data Index: 367442 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.5106. Min Act: -0.0001

Data Index: 382517 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.4908. Min Act: -0.0001

Data Index: 1274287 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.3806. Min Act: -0.0001

Data Index: 1356335 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.3658. Min Act: -0.0001

Data Index: 1039064 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.3717. Min Act: -0.0001

Data Index: 509798 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.3212. Min Act: -0.0001

Data Index: 419470 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.3222. Min Act: -0.0001

Data Index: 890313 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.3388. Min Act: -0.0001

Data Index: 24470 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.2475. Min Act: -0.0001

Data Index: 115958 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.1710. Min Act: -0.0001

Data Index: 1303228 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.2801. Min Act: -0.0001

Data Index: 899282 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.0923. Min Act: -0.0001

Data Index: 134892 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.2314. Min Act: -0.0001

Data Index: 113114 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.2843. Min Act: -0.0001

Data Index: 249130 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.2011. Min Act: -0.0001

Data Index: 519334 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.1527. Min Act: -0.0001

Data Index: 61183 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.1913. Min Act: -0.0001

Data Index: 1060779 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.2246. Min Act: -0.0001

Data Index: 409700 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 1.5503. Min Range: -1.5503

Max Act: 1.1015. Min Act: -0.0001

Data Index: 589494 (C4 (Web Text))

Max Activating Token Index: 559