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

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

Neuron 3653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0634. Min Range: -1.0634

Max Act: 1.0634. Min Act: -0.0000

Data Index: 450536 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.9869. Min Act: -0.0000

Data Index: 195154 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.9577. Min Act: -0.0000

Data Index: 84186 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1181646 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1146862 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1111865 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7877. Min Act: -0.0000

Data Index: 760847 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7983. Min Act: -0.0000

Data Index: 873079 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7662. Min Act: -0.0000

Data Index: 581270 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7519. Min Act: -0.0000

Data Index: 359383 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7950. Min Act: -0.0000

Data Index: 703377 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7479. Min Act: -0.0000

Data Index: 151925 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7670. Min Act: -0.0000

Data Index: 369794 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1123253 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7161. Min Act: -0.0000

Data Index: 481484 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1391320 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7583. Min Act: -0.0000

Data Index: 970347 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7505. Min Act: -0.0000

Data Index: 49678 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1052413 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 1.0634. Min Range: -1.0634

Max Act: 0.7443. Min Act: -0.0000

Data Index: 97334 (C4 (Web Text))

Max Activating Token Index: 309