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

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

Neuron 4823 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: 5.1887. Min Range: -5.1887

Max Act: 5.0896. Min Act: -0.0000

Data Index: 1103372 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 5.1887. Min Range: -5.1887

Max Act: 5.1887. Min Act: -0.0000

Data Index: 976722 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.6286. Min Act: -0.0000

Data Index: 1642711 (Python Code)

Max Activating Token Index: 195

Text #3

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.5591. Min Act: -0.0000

Data Index: 25867 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.4963. Min Act: -0.0000

Data Index: 1000847 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.4523. Min Act: -0.0000

Data Index: 1311502 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.4428. Min Act: -0.0000

Data Index: 1003747 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.5464. Min Act: -0.0000

Data Index: 1127752 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.5018. Min Act: -0.0000

Data Index: 25377 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.6401. Min Act: -0.0000

Data Index: 875192 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.6548. Min Act: -0.0000

Data Index: 793901 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.4786. Min Act: -0.0000

Data Index: 1221091 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.2518. Min Act: -0.0000

Data Index: 1173186 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.1947. Min Act: -0.0000

Data Index: 941447 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.3372. Min Act: -0.0000

Data Index: 781474 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.1722. Min Act: -0.0000

Data Index: 1136209 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.4930. Min Act: -0.0000

Data Index: 412584 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.3068. Min Act: -0.0000

Data Index: 805303 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.2776. Min Act: -0.0000

Data Index: 79382 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 5.1887. Min Range: -5.1887

Max Act: 4.1176. Min Act: -0.0000

Data Index: 1306654 (C4 (Web Text))

Max Activating Token Index: 289