Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2974 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.6527. Min Act: -0.0001

Data Index: 1155546 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2887. Min Act: -0.0001

Data Index: 411992 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.5934. Min Act: -0.0001

Data Index: 629852 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.4295. Min Act: -0.0001

Data Index: 552674 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.6171. Min Act: -0.0001

Data Index: 334841 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2673. Min Act: -0.0001

Data Index: 769132 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3053. Min Act: -0.0001

Data Index: 36330 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3986. Min Act: -0.0001

Data Index: 480242 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2183. Min Act: -0.0001

Data Index: 509442 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2170. Min Act: -0.0001

Data Index: 26539 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2488. Min Act: -0.0001

Data Index: 1046760 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2952. Min Act: -0.0001

Data Index: 564675 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2892. Min Act: -0.0001

Data Index: 805672 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2053. Min Act: -0.0001

Data Index: 858708 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.0329. Min Act: -0.0001

Data Index: 1289417 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.1542. Min Act: -0.0001

Data Index: 350062 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.1868. Min Act: -0.0001

Data Index: 645047 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2084. Min Act: -0.0001

Data Index: 577570 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2457. Min Act: -0.0001

Data Index: 1219753 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2837. Min Act: -0.0001

Data Index: 1010176 (C4 (Web Text))

Max Activating Token Index: 363