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

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

Neuron 5532 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0001

Data Index: 638505 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1121967 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0486. Min Act: -0.0001

Data Index: 38320 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0475. Min Act: -0.0001

Data Index: 533555 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0468. Min Act: -0.0001

Data Index: 471714 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0468. Min Act: -0.0001

Data Index: 830031 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1178894 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0475. Min Act: -0.0001

Data Index: 158081 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0462. Min Act: -0.0001

Data Index: 1343578 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0466. Min Act: -0.0001

Data Index: 419054 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0460. Min Act: -0.0001

Data Index: 245984 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1033917 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0454. Min Act: -0.0001

Data Index: 701069 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1138416 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1335211 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0461. Min Act: -0.0001

Data Index: 444197 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0461. Min Act: -0.0001

Data Index: 564401 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0461. Min Act: -0.0001

Data Index: 256755 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0461. Min Act: -0.0001

Data Index: 52021 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0461. Min Act: -0.0001

Data Index: 549856 (C4 (Web Text))

Max Activating Token Index: 3