Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3261 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3169. Min Range: -2.3169

Max Act: 2.2740. Min Act: -0.0000

Data Index: 255036 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 2.3169. Min Range: -2.3169

Max Act: 2.3169. Min Act: -0.0000

Data Index: 351784 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 2.3169. Min Range: -2.3169

Max Act: 2.0353. Min Act: -0.0000

Data Index: 766454 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 2.3169. Min Range: -2.3169

Max Act: 2.1110. Min Act: -0.0000

Data Index: 771945 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 2.3169. Min Range: -2.3169

Max Act: 2.1277. Min Act: -0.0000

Data Index: 931893 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 2.3169. Min Range: -2.3169

Max Act: 2.0429. Min Act: -0.0000

Data Index: 826398 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.9693. Min Act: -0.0000

Data Index: 296143 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 2.3169. Min Range: -2.3169

Max Act: 2.0125. Min Act: -0.0000

Data Index: 866440 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.8567. Min Act: -0.0000

Data Index: 457372 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.8665. Min Act: -0.0000

Data Index: 289616 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.7495. Min Act: -0.0000

Data Index: 89309 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.9077. Min Act: -0.0000

Data Index: 681649 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 2.3169. Min Range: -2.3169

Max Act: 2.1524. Min Act: -0.0000

Data Index: 534437 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.8077. Min Act: -0.0000

Data Index: 610382 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.9936. Min Act: -0.0000

Data Index: 626785 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.8715. Min Act: -0.0000

Data Index: 1104746 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.8278. Min Act: -0.0000

Data Index: 511366 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.7529. Min Act: -0.0000

Data Index: 804555 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.7566. Min Act: -0.0000

Data Index: 1280896 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 2.3169. Min Range: -2.3169

Max Act: 1.6581. Min Act: -0.0000

Data Index: 324983 (C4 (Web Text))

Max Activating Token Index: 393