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

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

Neuron 4563 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: 1.9870. Min Range: -1.9870

Max Act: 1.9870. Min Act: -0.0000

Data Index: 1027435 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.4825. Min Act: -0.0000

Data Index: 1362515 (Python Code)

Max Activating Token Index: 981

Text #2

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1347909 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.5240. Min Act: -0.0000

Data Index: 1547148 (Python Code)

Max Activating Token Index: 959

Text #4

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.5351. Min Act: -0.0000

Data Index: 673272 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.5019. Min Act: -0.0000

Data Index: 1602563 (Python Code)

Max Activating Token Index: 949

Text #6

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.4762. Min Act: -0.0000

Data Index: 1577877 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.4086. Min Act: -0.0000

Data Index: 758032 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.4487. Min Act: -0.0000

Data Index: 222111 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.4405. Min Act: -0.0000

Data Index: 200335 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.3411. Min Act: -0.0000

Data Index: 1293611 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1528908 (Python Code)

Max Activating Token Index: 661

Text #12

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.3850. Min Act: -0.0000

Data Index: 1581742 (Python Code)

Max Activating Token Index: 440

Text #13

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.3560. Min Act: -0.0000

Data Index: 1513322 (Python Code)

Max Activating Token Index: 934

Text #14

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1383708 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1484371 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1503627 (Python Code)

Max Activating Token Index: 788

Text #17

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.3491. Min Act: -0.0000

Data Index: 1607749 (Python Code)

Max Activating Token Index: 122

Text #18

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.3372. Min Act: -0.0000

Data Index: 1651830 (Python Code)

Max Activating Token Index: 106

Text #19

Max Range: 1.9870. Min Range: -1.9870

Max Act: 1.3011. Min Act: -0.0000

Data Index: 1610036 (Python Code)

Max Activating Token Index: 447