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

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

Neuron 705 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.8902. Min Act: -0.0001

Data Index: 924275 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.9426. Min Act: -0.0001

Data Index: 652973 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.8524. Min Act: -0.0001

Data Index: 828919 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.7449. Min Act: -0.0001

Data Index: 859184 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.6382. Min Act: -0.0001

Data Index: 740916 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.6472. Min Act: -0.0001

Data Index: 1329587 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.5785. Min Act: -0.0001

Data Index: 339136 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.6870. Min Act: -0.0001

Data Index: 1045842 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.6663. Min Act: -0.0001

Data Index: 347117 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.7506. Min Act: -0.0001

Data Index: 430855 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.6145. Min Act: -0.0001

Data Index: 478265 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.3262. Min Act: -0.0001

Data Index: 460266 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.3006. Min Act: -0.0001

Data Index: 876212 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.3926. Min Act: -0.0001

Data Index: 167502 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.2905. Min Act: -0.0001

Data Index: 390520 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.3498. Min Act: -0.0001

Data Index: 486021 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.3297. Min Act: -0.0001

Data Index: 1281022 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.2654. Min Act: -0.0001

Data Index: 1049028 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.3259. Min Act: -0.0001

Data Index: 804945 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.9426. Min Range: -1.9426

Max Act: 1.2402. Min Act: -0.0001

Data Index: 807814 (C4 (Web Text))

Max Activating Token Index: 183