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

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

Neuron 4539 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2831. Min Act: -0.0000

Data Index: 673494 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1149583 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2619. Min Act: -0.0001

Data Index: 765703 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2581. Min Act: -0.0000

Data Index: 819288 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2466. Min Act: -0.0001

Data Index: 848766 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2477. Min Act: -0.0001

Data Index: 651111 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2187. Min Act: -0.0000

Data Index: 55660 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2520. Min Act: -0.0001

Data Index: 134607 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2313. Min Act: -0.0000

Data Index: 461562 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2267. Min Act: -0.0000

Data Index: 465078 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1135450 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2161. Min Act: -0.0000

Data Index: 70256 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1963. Min Act: -0.0000

Data Index: 1294023 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1912. Min Act: -0.0001

Data Index: 530091 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1797. Min Act: -0.0001

Data Index: 999044 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2049. Min Act: -0.0000

Data Index: 958088 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1932. Min Act: -0.0000

Data Index: 486489 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1899. Min Act: -0.0000

Data Index: 386218 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1098602 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1956. Min Act: -0.0000

Data Index: 43788 (C4 (Web Text))

Max Activating Token Index: 124