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

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

Neuron 2622 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.6507. Min Act: -0.0000

Data Index: 696720 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1042478 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4494. Min Act: -0.0000

Data Index: 272547 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4649. Min Act: -0.0000

Data Index: 10298 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1129011 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4817. Min Act: -0.0000

Data Index: 864292 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4474. Min Act: -0.0000

Data Index: 143763 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1496014 (Python Code)

Max Activating Token Index: 955

Text #8

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4716. Min Act: -0.0000

Data Index: 494835 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1561149 (Python Code)

Max Activating Token Index: 666

Text #10

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4550. Min Act: -0.0000

Data Index: 45996 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4008. Min Act: -0.0000

Data Index: 667210 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1396435 (Python Code)

Max Activating Token Index: 679

Text #13

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1445604 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1498347 (Python Code)

Max Activating Token Index: 212

Text #15

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1507521 (Python Code)

Max Activating Token Index: 858

Text #16

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1020494 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1287183 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1636472 (Python Code)

Max Activating Token Index: 832

Text #19

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1380626 (Python Code)

Max Activating Token Index: 849