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

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

Neuron 1648 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.9515. Min Act: -0.0000

Data Index: 332283 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.9509. Min Act: -0.0000

Data Index: 1104540 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.9346. Min Act: -0.0000

Data Index: 849568 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.9424. Min Act: -0.0000

Data Index: 1337624 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.9433. Min Act: -0.0000

Data Index: 340283 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.7739. Min Act: -0.0000

Data Index: 1219392 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.8500. Min Act: -0.0000

Data Index: 75957 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.4055. Min Act: -0.0000

Data Index: 396376 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.3003. Min Act: -0.0000

Data Index: 1234582 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.1406. Min Act: -0.0000

Data Index: 692009 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.1963. Min Act: -0.0000

Data Index: 318198 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.1877. Min Act: -0.0000

Data Index: 108151 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.1481. Min Act: -0.0000

Data Index: 617577 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1267974 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.1121. Min Act: -0.0000

Data Index: 468162 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.0951. Min Act: -0.0000

Data Index: 274414 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1077746 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.0387. Min Act: -0.0000

Data Index: 66839 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.0949. Min Act: -0.0000

Data Index: 745625 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.1108. Min Act: -0.0000

Data Index: 740362 (C4 (Web Text))

Max Activating Token Index: 456