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

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

Neuron 2991 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: 5.5039. Min Range: -5.5039

Max Act: 5.5039. Min Act: -0.0000

Data Index: 537253 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 5.5039. Min Range: -5.5039

Max Act: 5.3340. Min Act: -0.0000

Data Index: 1177206 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 5.5039. Min Range: -5.5039

Max Act: 4.9394. Min Act: -0.0000

Data Index: 229598 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 5.5039. Min Range: -5.5039

Max Act: 5.1322. Min Act: -0.0000

Data Index: 660399 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 5.5039. Min Range: -5.5039

Max Act: 5.0441. Min Act: -0.0000

Data Index: 57445 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 5.5039. Min Range: -5.5039

Max Act: 4.9081. Min Act: -0.0000

Data Index: 215863 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 5.5039. Min Range: -5.5039

Max Act: 4.2624. Min Act: -0.0000

Data Index: 918114 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 5.5039. Min Range: -5.5039

Max Act: 4.2772. Min Act: -0.0000

Data Index: 680473 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 5.5039. Min Range: -5.5039

Max Act: 3.4686. Min Act: -0.0000

Data Index: 261786 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 5.5039. Min Range: -5.5039

Max Act: 3.2663. Min Act: -0.0000

Data Index: 664379 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 5.5039. Min Range: -5.5039

Max Act: 3.2346. Min Act: -0.0000

Data Index: 1098707 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 5.5039. Min Range: -5.5039

Max Act: 3.0634. Min Act: -0.0000

Data Index: 821813 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 5.5039. Min Range: -5.5039

Max Act: 3.3230. Min Act: -0.0000

Data Index: 1292719 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 5.5039. Min Range: -5.5039

Max Act: 3.1326. Min Act: -0.0000

Data Index: 556434 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 5.5039. Min Range: -5.5039

Max Act: 2.7337. Min Act: -0.0000

Data Index: 194703 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 5.5039. Min Range: -5.5039

Max Act: 2.4204. Min Act: -0.0000

Data Index: 1120500 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 5.5039. Min Range: -5.5039

Max Act: 2.6232. Min Act: -0.0000

Data Index: 1236781 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 5.5039. Min Range: -5.5039

Max Act: 2.4284. Min Act: -0.0000

Data Index: 149325 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 5.5039. Min Range: -5.5039

Max Act: 2.4208. Min Act: -0.0000

Data Index: 77021 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 5.5039. Min Range: -5.5039

Max Act: 2.4281. Min Act: -0.0000

Data Index: 161253 (C4 (Web Text))

Max Activating Token Index: 897