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

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

Neuron 2367 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7958. Min Range: -2.7958

Max Act: 2.7958. Min Act: -0.0000

Data Index: 1065640 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 2.7958. Min Range: -2.7958

Max Act: 2.4842. Min Act: -0.0000

Data Index: 1136579 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 2.7958. Min Range: -2.7958

Max Act: 2.3410. Min Act: -0.0000

Data Index: 340258 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 2.7958. Min Range: -2.7958

Max Act: 2.3553. Min Act: -0.0000

Data Index: 228182 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 2.7958. Min Range: -2.7958

Max Act: 2.2443. Min Act: -0.0000

Data Index: 1153312 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 2.7958. Min Range: -2.7958

Max Act: 2.0911. Min Act: -0.0000

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 2.7958. Min Range: -2.7958

Max Act: 2.2341. Min Act: -0.0000

Data Index: 1127943 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 2.7958. Min Range: -2.7958

Max Act: 2.2503. Min Act: -0.0000

Data Index: 445221 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 2.7958. Min Range: -2.7958

Max Act: 2.0215. Min Act: -0.0000

Data Index: 1084918 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.9925. Min Act: -0.0000

Data Index: 308786 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.8436. Min Act: -0.0000

Data Index: 582631 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.8066. Min Act: -0.0000

Data Index: 472078 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.7945. Min Act: -0.0000

Data Index: 348686 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.8792. Min Act: -0.0000

Data Index: 86550 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.6746. Min Act: -0.0000

Data Index: 1078167 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.9673. Min Act: -0.0000

Data Index: 1091891 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.7526. Min Act: -0.0000

Data Index: 263533 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.8548. Min Act: -0.0000

Data Index: 915840 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.8264. Min Act: -0.0000

Data Index: 1246832 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 2.7958. Min Range: -2.7958

Max Act: 1.8208. Min Act: -0.0000

Data Index: 1018884 (C4 (Web Text))

Max Activating Token Index: 547