Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3998 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.3373. Min Range: -2.3373

Max Act: 2.3373. Min Act: -0.0001

Data Index: 159755 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.7809. Min Act: -0.0000

Data Index: 33081 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.6873. Min Act: -0.0000

Data Index: 682983 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.5248. Min Act: -0.0000

Data Index: 504086 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.7088. Min Act: -0.0000

Data Index: 345825 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.4596. Min Act: -0.0001

Data Index: 748128 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.4604. Min Act: -0.0001

Data Index: 579992 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.4803. Min Act: -0.0000

Data Index: 131345 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.3705. Min Act: -0.0000

Data Index: 888101 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.3977. Min Act: -0.0000

Data Index: 633351 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.3578. Min Act: -0.0000

Data Index: 490096 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.3810. Min Act: -0.0001

Data Index: 725426 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.3276. Min Act: -0.0001

Data Index: 157765 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.3009. Min Act: -0.0001

Data Index: 708834 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.2094. Min Act: -0.0000

Data Index: 131717 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.2116. Min Act: -0.0001

Data Index: 1348378 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.2836. Min Act: -0.0001

Data Index: 190293 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.1569. Min Act: -0.0001

Data Index: 346294 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.2129. Min Act: -0.0001

Data Index: 1345681 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 2.3373. Min Range: -2.3373

Max Act: 1.1728. Min Act: -0.0000

Data Index: 571880 (C4 (Web Text))

Max Activating Token Index: 823