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

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

Neuron 2540 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7069. Min Range: -3.7069

Max Act: 3.7069. Min Act: -0.0000

Data Index: 938571 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 3.7069. Min Range: -3.7069

Max Act: 3.1883. Min Act: -0.0000

Data Index: 1634809 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.9953. Min Act: -0.0000

Data Index: 577942 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.9956. Min Act: -0.0000

Data Index: 29216 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 3.7069. Min Range: -3.7069

Max Act: 3.5441. Min Act: -0.0000

Data Index: 1263719 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.9626. Min Act: -0.0000

Data Index: 373539 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.7649. Min Act: -0.0000

Data Index: 523901 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.6687. Min Act: -0.0000

Data Index: 958373 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.6251. Min Act: -0.0000

Data Index: 63942 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.7399. Min Act: -0.0000

Data Index: 956655 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.7273. Min Act: -0.0000

Data Index: 735425 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.5770. Min Act: -0.0000

Data Index: 383508 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.7135. Min Act: -0.0000

Data Index: 1599993 (Python Code)

Max Activating Token Index: 883

Text #13

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.2488. Min Act: -0.0000

Data Index: 344712 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.4996. Min Act: -0.0000

Data Index: 608225 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.4533. Min Act: -0.0000

Data Index: 1111598 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.3342. Min Act: -0.0000

Data Index: 455801 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.5811. Min Act: -0.0000

Data Index: 1022053 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.3172. Min Act: -0.0000

Data Index: 932288 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 3.7069. Min Range: -3.7069

Max Act: 2.2862. Min Act: -0.0000

Data Index: 986860 (C4 (Web Text))

Max Activating Token Index: 582