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

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

Neuron 1679 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: 2.6949. Min Range: -2.6949

Max Act: 2.6949. Min Act: -0.0000

Data Index: 1129649 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 2.6949. Min Range: -2.6949

Max Act: 2.3305. Min Act: -0.0000

Data Index: 105124 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 2.6949. Min Range: -2.6949

Max Act: 2.1906. Min Act: -0.0000

Data Index: 29136 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 2.6949. Min Range: -2.6949

Max Act: 2.0087. Min Act: -0.0000

Data Index: 313950 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 2.6949. Min Range: -2.6949

Max Act: 2.0650. Min Act: -0.0000

Data Index: 62425 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 2.6949. Min Range: -2.6949

Max Act: 2.0258. Min Act: -0.0000

Data Index: 594726 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.9216. Min Act: -0.0000

Data Index: 664386 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.9734. Min Act: -0.0000

Data Index: 408751 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 2.6949. Min Range: -2.6949

Max Act: 2.0168. Min Act: -0.0000

Data Index: 428596 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.7974. Min Act: -0.0000

Data Index: 906503 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.6771. Min Act: -0.0000

Data Index: 903674 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1245001 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.8442. Min Act: -0.0000

Data Index: 123151 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.6183. Min Act: -0.0000

Data Index: 1242823 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.8682. Min Act: -0.0000

Data Index: 1001666 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.7545. Min Act: -0.0000

Data Index: 35850 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.6225. Min Act: -0.0000

Data Index: 150740 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.6134. Min Act: -0.0000

Data Index: 741790 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.6974. Min Act: -0.0000

Data Index: 588451 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 2.6949. Min Range: -2.6949

Max Act: 1.7946. Min Act: -0.0000

Data Index: 95572 (C4 (Web Text))

Max Activating Token Index: 241