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

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

Neuron 744 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4376. Min Range: -4.4376

Max Act: 4.4376. Min Act: -0.0000

Data Index: 13946 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 4.4376. Min Range: -4.4376

Max Act: 3.5169. Min Act: -0.0000

Data Index: 131166 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 4.4376. Min Range: -4.4376

Max Act: 3.4327. Min Act: -0.0000

Data Index: 51380 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 4.4376. Min Range: -4.4376

Max Act: 3.0410. Min Act: -0.0000

Data Index: 1081941 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 4.4376. Min Range: -4.4376

Max Act: 3.3146. Min Act: -0.0000

Data Index: 680081 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 4.4376. Min Range: -4.4376

Max Act: 3.1438. Min Act: -0.0000

Data Index: 1146043 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 4.4376. Min Range: -4.4376

Max Act: 3.1424. Min Act: -0.0000

Data Index: 319891 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 4.4376. Min Range: -4.4376

Max Act: 2.9332. Min Act: -0.0000

Data Index: 202662 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 4.4376. Min Range: -4.4376

Max Act: 3.2340. Min Act: -0.0000

Data Index: 479797 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 4.4376. Min Range: -4.4376

Max Act: 3.0325. Min Act: -0.0000

Data Index: 861958 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 4.4376. Min Range: -4.4376

Max Act: 2.9910. Min Act: -0.0000

Data Index: 877303 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 4.4376. Min Range: -4.4376

Max Act: 2.6814. Min Act: -0.0000

Data Index: 25121 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 4.4376. Min Range: -4.4376

Max Act: 3.0834. Min Act: -0.0000

Data Index: 279875 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 4.4376. Min Range: -4.4376

Max Act: 2.7453. Min Act: -0.0000

Data Index: 189135 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 4.4376. Min Range: -4.4376

Max Act: 2.8876. Min Act: -0.0000

Data Index: 549225 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 4.4376. Min Range: -4.4376

Max Act: 2.6748. Min Act: -0.0000

Data Index: 764130 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 4.4376. Min Range: -4.4376

Max Act: 2.7124. Min Act: -0.0000

Data Index: 766005 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 4.4376. Min Range: -4.4376

Max Act: 2.8429. Min Act: -0.0000

Data Index: 49619 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 4.4376. Min Range: -4.4376

Max Act: 2.9575. Min Act: -0.0000

Data Index: 200136 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 4.4376. Min Range: -4.4376

Max Act: 2.8195. Min Act: -0.0000

Data Index: 276298 (C4 (Web Text))

Max Activating Token Index: 300