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

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

Neuron 5937 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: 2.8787. Min Range: -2.8787

Max Act: 2.8429. Min Act: -0.0000

Data Index: 1444843 (Python Code)

Max Activating Token Index: 314

Text #1

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.5955. Min Act: -0.0000

Data Index: 1458404 (Python Code)

Max Activating Token Index: 132

Text #2

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.8787. Min Act: -0.0000

Data Index: 1503975 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.5076. Min Act: -0.0000

Data Index: 1477878 (Python Code)

Max Activating Token Index: 385

Text #4

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.6070. Min Act: -0.0000

Data Index: 1502938 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.4574. Min Act: -0.0000

Data Index: 1631104 (Python Code)

Max Activating Token Index: 825

Text #6

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.5493. Min Act: -0.0000

Data Index: 1466765 (Python Code)

Max Activating Token Index: 457

Text #7

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.5466. Min Act: -0.0000

Data Index: 1486552 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.6738. Min Act: -0.0000

Data Index: 1553354 (Python Code)

Max Activating Token Index: 983

Text #9

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.4895. Min Act: -0.0000

Data Index: 1467595 (Python Code)

Max Activating Token Index: 838

Text #10

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.3588. Min Act: -0.0000

Data Index: 1646863 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.4691. Min Act: -0.0000

Data Index: 1427715 (Python Code)

Max Activating Token Index: 1015

Text #12

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.3157. Min Act: -0.0000

Data Index: 1500450 (Python Code)

Max Activating Token Index: 367

Text #13

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.4145. Min Act: -0.0000

Data Index: 1475301 (Python Code)

Max Activating Token Index: 757

Text #14

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.4166. Min Act: -0.0000

Data Index: 1511116 (Python Code)

Max Activating Token Index: 259

Text #15

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.3872. Min Act: -0.0000

Data Index: 1649796 (Python Code)

Max Activating Token Index: 596

Text #16

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.2456. Min Act: -0.0000

Data Index: 1559938 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.0895. Min Act: -0.0000

Data Index: 1393984 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.1149. Min Act: -0.0000

Data Index: 1435635 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.2294. Min Act: -0.0000

Data Index: 1586268 (Python Code)

Max Activating Token Index: 15