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

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

Neuron 3627 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.5199. Min Act: -0.0000

Data Index: 805377 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1608. Min Act: -0.0000

Data Index: 471415 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.4386. Min Act: -0.0000

Data Index: 251064 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0437. Min Act: -0.0000

Data Index: 322680 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.3144. Min Act: -0.0000

Data Index: 728321 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 1.5199. Min Range: -1.5199

Max Act: 0.8946. Min Act: -0.0000

Data Index: 509259 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0175. Min Act: -0.0000

Data Index: 425728 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1429. Min Act: -0.0000

Data Index: 276981 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1365. Min Act: -0.0000

Data Index: 296394 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0193. Min Act: -0.0000

Data Index: 328450 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1251360 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0448. Min Act: -0.0000

Data Index: 162318 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 1.5199. Min Range: -1.5199

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1223306 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0331. Min Act: -0.0000

Data Index: 641954 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 1.5199. Min Range: -1.5199

Max Act: 0.9606. Min Act: -0.0000

Data Index: 900897 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 1.5199. Min Range: -1.5199

Max Act: 0.9084. Min Act: -0.0000

Data Index: 856204 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.5199. Min Range: -1.5199

Max Act: 0.8747. Min Act: -0.0000

Data Index: 189649 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.5199. Min Range: -1.5199

Max Act: 0.9501. Min Act: -0.0000

Data Index: 841946 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.5199. Min Range: -1.5199

Max Act: 0.9061. Min Act: -0.0000

Data Index: 282778 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 1.5199. Min Range: -1.5199

Max Act: 0.8590. Min Act: -0.0000

Data Index: 949282 (C4 (Web Text))

Max Activating Token Index: 369