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

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

Neuron 2054 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.9586. Min Act: -0.0000

Data Index: 939997 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.9409. Min Act: -0.0000

Data Index: 351814 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1136037 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.8736. Min Act: -0.0000

Data Index: 683396 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.8104. Min Act: -0.0001

Data Index: 996409 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.8025. Min Act: -0.0000

Data Index: 40221 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7839. Min Act: -0.0000

Data Index: 647921 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7990. Min Act: -0.0001

Data Index: 816727 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7333. Min Act: -0.0000

Data Index: 505804 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7225. Min Act: -0.0000

Data Index: 1356404 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1307997 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7094. Min Act: -0.0000

Data Index: 874992 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7181. Min Act: -0.0001

Data Index: 176192 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6993. Min Act: -0.0000

Data Index: 224421 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1094102 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7011. Min Act: -0.0001

Data Index: 950909 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7127. Min Act: 0.0000

Data Index: 123938 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7252. Min Act: -0.0000

Data Index: 50766 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6408. Min Act: -0.0000

Data Index: 614961 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6542. Min Act: -0.0001

Data Index: 633323 (C4 (Web Text))

Max Activating Token Index: 394