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

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

Neuron 5074 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: 2.4179. Min Range: -2.4179

Max Act: 2.4179. Min Act: -0.0000

Data Index: 575385 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 2.4179. Min Range: -2.4179

Max Act: 2.0345. Min Act: -0.0000

Data Index: 13257 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 2.4179. Min Range: -2.4179

Max Act: 2.1009. Min Act: -0.0000

Data Index: 889401 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 2.4179. Min Range: -2.4179

Max Act: 2.1913. Min Act: -0.0000

Data Index: 1258611 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 2.4179. Min Range: -2.4179

Max Act: 2.0506. Min Act: -0.0000

Data Index: 508943 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.9598. Min Act: -0.0000

Data Index: 1235836 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.9391. Min Act: -0.0000

Data Index: 829596 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 2.4179. Min Range: -2.4179

Max Act: 2.0155. Min Act: -0.0000

Data Index: 63352 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.6634. Min Act: -0.0000

Data Index: 570162 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.5839. Min Act: -0.0000

Data Index: 915217 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.8456. Min Act: -0.0000

Data Index: 102050 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.7140. Min Act: -0.0000

Data Index: 20386 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.6010. Min Act: -0.0000

Data Index: 1235457 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.5842. Min Act: -0.0000

Data Index: 68905 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.7280. Min Act: -0.0000

Data Index: 636799 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.5973. Min Act: -0.0000

Data Index: 879076 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.5855. Min Act: -0.0000

Data Index: 30915 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.6880. Min Act: -0.0000

Data Index: 1434 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.6630. Min Act: -0.0000

Data Index: 938198 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 2.4179. Min Range: -2.4179

Max Act: 1.4688. Min Act: -0.0000

Data Index: 36774 (C4 (Web Text))

Max Activating Token Index: 696