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

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

Neuron 798 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: 3.3912. Min Range: -3.3912

Max Act: 3.3563. Min Act: -0.0000

Data Index: 1346416 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 3.3912. Min Range: -3.3912

Max Act: 3.3912. Min Act: -0.0000

Data Index: 1375043 (Python Code)

Max Activating Token Index: 347

Text #2

Max Range: 3.3912. Min Range: -3.3912

Max Act: 3.0415. Min Act: -0.0000

Data Index: 1655020 (Python Code)

Max Activating Token Index: 572

Text #3

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.8136. Min Act: -0.0000

Data Index: 788562 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.6510. Min Act: -0.0000

Data Index: 617348 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.6237. Min Act: -0.0000

Data Index: 117319 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.7064. Min Act: -0.0000

Data Index: 1294325 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.5712. Min Act: -0.0000

Data Index: 1129367 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.6158. Min Act: -0.0000

Data Index: 412087 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.6667. Min Act: -0.0000

Data Index: 739753 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.5271. Min Act: -0.0000

Data Index: 1107956 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.5304. Min Act: -0.0000

Data Index: 1340978 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.5304. Min Act: -0.0000

Data Index: 1277350 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.6049. Min Act: -0.0000

Data Index: 105845 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.4458. Min Act: -0.0000

Data Index: 219011 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.5203. Min Act: -0.0000

Data Index: 1559909 (Python Code)

Max Activating Token Index: 838

Text #16

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.5016. Min Act: -0.0000

Data Index: 982400 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.5103. Min Act: -0.0000

Data Index: 700841 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.3363. Min Act: -0.0000

Data Index: 137040 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 3.3912. Min Range: -3.3912

Max Act: 2.2973. Min Act: -0.0000

Data Index: 1486603 (Python Code)

Max Activating Token Index: 602