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

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

Neuron 921 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: 1.7956. Min Range: -1.7956

Max Act: 1.7956. Min Act: -0.0000

Data Index: 931590 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.5332. Min Act: -0.0000

Data Index: 324733 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.3471. Min Act: -0.0000

Data Index: 49319 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.2722. Min Act: -0.0000

Data Index: 1212680 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.1975. Min Act: -0.0000

Data Index: 991220 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.1896. Min Act: -0.0000

Data Index: 584929 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.1413. Min Act: -0.0000

Data Index: 87477 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.0495. Min Act: -0.0000

Data Index: 654098 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1076932 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.9958. Min Act: -0.0000

Data Index: 175361 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.7956. Min Range: -1.7956

Max Act: 1.0086. Min Act: -0.0000

Data Index: 965821 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.9182. Min Act: -0.0000

Data Index: 58807 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1054923 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.9054. Min Act: -0.0000

Data Index: 176545 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.8449. Min Act: -0.0000

Data Index: 257283 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.8978. Min Act: -0.0000

Data Index: 824632 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.9456. Min Act: -0.0000

Data Index: 1075153 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.8813. Min Act: -0.0000

Data Index: 512280 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.8225. Min Act: -0.0000

Data Index: 912970 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 1.7956. Min Range: -1.7956

Max Act: 0.8593. Min Act: -0.0000

Data Index: 134525 (C4 (Web Text))

Max Activating Token Index: 50