Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5169 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7682. Min Range: -3.7682

Max Act: 3.7682. Min Act: -0.0000

Data Index: 1010307 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.9373. Min Act: -0.0000

Data Index: 304798 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.5518. Min Act: -0.0000

Data Index: 1588042 (Python Code)

Max Activating Token Index: 674

Text #3

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.4913. Min Act: -0.0000

Data Index: 103779 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.3542. Min Act: -0.0000

Data Index: 535259 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.3384. Min Act: -0.0000

Data Index: 1297427 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.1175. Min Act: -0.0000

Data Index: 455672 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.2207. Min Act: -0.0000

Data Index: 107421 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.3406. Min Act: -0.0000

Data Index: 566910 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.0710. Min Act: -0.0000

Data Index: 420841 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.0927. Min Act: -0.0000

Data Index: 77878 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.0928. Min Act: -0.0000

Data Index: 597946 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.0653. Min Act: -0.0000

Data Index: 1023837 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.1550. Min Act: -0.0000

Data Index: 1224996 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 3.7682. Min Range: -3.7682

Max Act: 1.7937. Min Act: -0.0000

Data Index: 709225 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 3.7682. Min Range: -3.7682

Max Act: 1.8903. Min Act: -0.0000

Data Index: 667101 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 3.7682. Min Range: -3.7682

Max Act: 1.9489. Min Act: -0.0000

Data Index: 352316 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 3.7682. Min Range: -3.7682

Max Act: 1.8341. Min Act: -0.0000

Data Index: 1536823 (Python Code)

Max Activating Token Index: 241

Text #18

Max Range: 3.7682. Min Range: -3.7682

Max Act: 1.8344. Min Act: -0.0000

Data Index: 818059 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 3.7682. Min Range: -3.7682

Max Act: 2.0170. Min Act: -0.0000

Data Index: 333984 (C4 (Web Text))

Max Activating Token Index: 800