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

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

Neuron 1340 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.2002. Min Act: -0.0001

Data Index: 1052825 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1861. Min Act: -0.0001

Data Index: 924780 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1088187 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1078067 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1657. Min Act: -0.0001

Data Index: 325643 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1567. Min Act: -0.0001

Data Index: 692169 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1512. Min Act: -0.0001

Data Index: 524471 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1562. Min Act: -0.0001

Data Index: 515089 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1509. Min Act: -0.0001

Data Index: 474523 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1610. Min Act: -0.0001

Data Index: 455186 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1305320 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1498. Min Act: -0.0001

Data Index: 606541 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1503. Min Act: -0.0000

Data Index: 309203 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1181667 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1428. Min Act: -0.0001

Data Index: 700321 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1469. Min Act: -0.0000

Data Index: 1174988 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1361. Min Act: -0.0001

Data Index: 67826 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1515. Min Act: -0.0001

Data Index: 588857 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1109361 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1051119 (C4 (Web Text))

Max Activating Token Index: 30