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

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

Neuron 366 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.6518. Min Act: -0.0001

Data Index: 1272108 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.6535. Min Act: -0.0001

Data Index: 1113904 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5974. Min Act: -0.0001

Data Index: 300108 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5843. Min Act: -0.0001

Data Index: 301706 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5928. Min Act: -0.0001

Data Index: 1351613 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5933. Min Act: -0.0001

Data Index: 511173 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5935. Min Act: -0.0001

Data Index: 649236 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5469. Min Act: -0.0001

Data Index: 1173237 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5841. Min Act: -0.0001

Data Index: 1535138 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5372. Min Act: -0.0001

Data Index: 504734 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.6138. Min Act: -0.0001

Data Index: 327021 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.4409. Min Act: -0.0001

Data Index: 710330 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5086. Min Act: -0.0001

Data Index: 297645 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.4517. Min Act: -0.0001

Data Index: 1004924 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.4882. Min Act: -0.0001

Data Index: 417370 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5765. Min Act: -0.0001

Data Index: 593755 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.5154. Min Act: -0.0001

Data Index: 193642 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.4697. Min Act: -0.0001

Data Index: 286009 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.4629. Min Act: -0.0001

Data Index: 249964 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 1.6535. Min Range: -1.6535

Max Act: 1.4542. Min Act: -0.0001

Data Index: 378840 (C4 (Web Text))

Max Activating Token Index: 802