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

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

Neuron 3761 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: 2.7803. Min Range: -2.7803

Max Act: 2.7803. Min Act: -0.0000

Data Index: 1325909 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 2.7803. Min Range: -2.7803

Max Act: 2.3087. Min Act: -0.0000

Data Index: 801930 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 2.7803. Min Range: -2.7803

Max Act: 2.0279. Min Act: -0.0000

Data Index: 1140611 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 2.7803. Min Range: -2.7803

Max Act: 2.0108. Min Act: -0.0000

Data Index: 795310 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.9439. Min Act: -0.0000

Data Index: 766233 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.7949. Min Act: -0.0000

Data Index: 1306232 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.7840. Min Act: -0.0000

Data Index: 1058306 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.6865. Min Act: -0.0000

Data Index: 778679 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.8021. Min Act: -0.0000

Data Index: 1329880 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.6530. Min Act: -0.0000

Data Index: 1136149 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.6403. Min Act: -0.0000

Data Index: 1168769 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.6244. Min Act: -0.0000

Data Index: 861926 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.5938. Min Act: -0.0000

Data Index: 183724 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.5990. Min Act: -0.0000

Data Index: 738926 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.5689. Min Act: -0.0000

Data Index: 119949 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.6532. Min Act: -0.0000

Data Index: 543440 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.5379. Min Act: -0.0000

Data Index: 889658 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.4378. Min Act: -0.0000

Data Index: 113885 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.4385. Min Act: -0.0000

Data Index: 618817 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 2.7803. Min Range: -2.7803

Max Act: 1.5256. Min Act: -0.0000

Data Index: 132501 (C4 (Web Text))

Max Activating Token Index: 867