Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2844 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.4717. Min Act: -0.0001

Data Index: 963511 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.4001. Min Act: -0.0001

Data Index: 81512 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.4064. Min Act: -0.0001

Data Index: 722401 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3810. Min Act: -0.0001

Data Index: 1484168 (Python Code)

Max Activating Token Index: 272

Text #4

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1118912 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3651. Min Act: -0.0001

Data Index: 1030549 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3470. Min Act: -0.0001

Data Index: 322411 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3658. Min Act: -0.0001

Data Index: 991673 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3386. Min Act: -0.0001

Data Index: 574554 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3585. Min Act: -0.0001

Data Index: 1167770 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3347. Min Act: -0.0001

Data Index: 972580 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3108. Min Act: -0.0001

Data Index: 620816 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3350. Min Act: -0.0001

Data Index: 1336057 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3438. Min Act: -0.0001

Data Index: 1220463 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3522. Min Act: -0.0001

Data Index: 1012983 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3299. Min Act: -0.0001

Data Index: 42457 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3264. Min Act: -0.0001

Data Index: 463253 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3289. Min Act: -0.0001

Data Index: 750991 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3494. Min Act: -0.0001

Data Index: 1007547 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.4717. Min Range: -0.4717

Max Act: 0.3372. Min Act: -0.0001

Data Index: 1139308 (C4 (Web Text))

Max Activating Token Index: 966