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

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

Neuron 1425 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.4516. Min Range: -9.4516

Max Act: 9.4516. Min Act: -0.0001

Data Index: 1052779 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 9.4516. Min Range: -9.4516

Max Act: 8.9243. Min Act: -0.0001

Data Index: 8802 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 9.4516. Min Range: -9.4516

Max Act: 8.0315. Min Act: -0.0001

Data Index: 1169395 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 9.4516. Min Range: -9.4516

Max Act: 7.8632. Min Act: -0.0000

Data Index: 489263 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 9.4516. Min Range: -9.4516

Max Act: 8.2355. Min Act: -0.0001

Data Index: 1168821 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.5872. Min Act: -0.0000

Data Index: 869899 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 9.4516. Min Range: -9.4516

Max Act: 7.2426. Min Act: -0.0001

Data Index: 276073 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.8491. Min Act: -0.0001

Data Index: 277353 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.7988. Min Act: -0.0001

Data Index: 761332 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.9058. Min Act: -0.0000

Data Index: 206262 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.3904. Min Act: -0.0000

Data Index: 991021 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.8447. Min Act: -0.0001

Data Index: 845275 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.8134. Min Act: -0.0000

Data Index: 1071625 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.5961. Min Act: -0.0000

Data Index: 474963 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.0581. Min Act: -0.0001

Data Index: 1026970 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.7496. Min Act: -0.0001

Data Index: 222123 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.5644. Min Act: -0.0001

Data Index: 223321 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.6963. Min Act: -0.0001

Data Index: 1075908 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.6425. Min Act: -0.0000

Data Index: 285716 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 9.4516. Min Range: -9.4516

Max Act: 6.3412. Min Act: -0.0001

Data Index: 1339122 (C4 (Web Text))

Max Activating Token Index: 353