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

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

Neuron 1506 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: 1.3711. Min Range: -1.3711

Max Act: 1.3711. Min Act: -0.0000

Data Index: 487482 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1373805 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.1000. Min Act: -0.0000

Data Index: 841951 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1156249 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1395325 (Python Code)

Max Activating Token Index: 318

Text #5

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0311. Min Act: -0.0000

Data Index: 309603 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1162342 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0093. Min Act: -0.0000

Data Index: 654628 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1284234 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0794. Min Act: -0.0000

Data Index: 817298 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0290. Min Act: -0.0000

Data Index: 689430 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.3711. Min Range: -1.3711

Max Act: 0.9852. Min Act: -0.0000

Data Index: 711545 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0249. Min Act: -0.0000

Data Index: 290942 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0191. Min Act: -0.0000

Data Index: 238921 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0093. Min Act: -0.0000

Data Index: 968566 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0108. Min Act: -0.0000

Data Index: 351161 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0785. Min Act: 0.0000

Data Index: 109462 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0725. Min Act: -0.0000

Data Index: 1625108 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.0060. Min Act: -0.0000

Data Index: 44486 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 1.3711. Min Range: -1.3711

Max Act: 0.9961. Min Act: -0.0000

Data Index: 333555 (C4 (Web Text))

Max Activating Token Index: 390