Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 867 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4311. Min Act: -0.0001

Data Index: 1137439 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4542. Min Act: -0.0001

Data Index: 223518 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4020. Min Act: -0.0001

Data Index: 853827 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3852. Min Act: -0.0001

Data Index: 448789 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3773. Min Act: -0.0001

Data Index: 110904 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3922. Min Act: -0.0001

Data Index: 585469 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3842. Min Act: -0.0001

Data Index: 805408 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4025. Min Act: -0.0001

Data Index: 396273 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3858. Min Act: -0.0001

Data Index: 51234 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3705. Min Act: -0.0001

Data Index: 66352 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3853. Min Act: -0.0001

Data Index: 814527 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3510. Min Act: -0.0001

Data Index: 258002 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3488. Min Act: -0.0001

Data Index: 127338 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3560. Min Act: -0.0001

Data Index: 1040281 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3618. Min Act: -0.0001

Data Index: 484220 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3669. Min Act: -0.0001

Data Index: 1205599 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3626. Min Act: -0.0001

Data Index: 1211440 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3327. Min Act: -0.0001

Data Index: 1257757 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2979. Min Act: -0.0001

Data Index: 540050 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3755. Min Act: -0.0001

Data Index: 401574 (C4 (Web Text))

Max Activating Token Index: 633