Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4931 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4011. Min Range: -2.4011

Max Act: 2.4011. Min Act: -0.0000

Data Index: 1496313 (Python Code)

Max Activating Token Index: 239

Text #1

Max Range: 2.4011. Min Range: -2.4011

Max Act: 2.3052. Min Act: -0.0000

Data Index: 1602593 (Python Code)

Max Activating Token Index: 172

Text #2

Max Range: 2.4011. Min Range: -2.4011

Max Act: 2.0887. Min Act: -0.0000

Data Index: 1645155 (Python Code)

Max Activating Token Index: 440

Text #3

Max Range: 2.4011. Min Range: -2.4011

Max Act: 2.0540. Min Act: -0.0000

Data Index: 1370291 (Python Code)

Max Activating Token Index: 567

Text #4

Max Range: 2.4011. Min Range: -2.4011

Max Act: 2.0246. Min Act: -0.0000

Data Index: 828721 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.7871. Min Act: -0.0000

Data Index: 1298020 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.8033. Min Act: -0.0000

Data Index: 1515498 (Python Code)

Max Activating Token Index: 303

Text #7

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.6729. Min Act: -0.0000

Data Index: 158131 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.7575. Min Act: -0.0000

Data Index: 668353 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.7359. Min Act: -0.0000

Data Index: 1498120 (Python Code)

Max Activating Token Index: 332

Text #10

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.7317. Min Act: -0.0000

Data Index: 1025655 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.6539. Min Act: -0.0000

Data Index: 1521263 (Python Code)

Max Activating Token Index: 646

Text #12

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.6462. Min Act: -0.0000

Data Index: 866839 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.7417. Min Act: -0.0000

Data Index: 348977 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1454859 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.5387. Min Act: -0.0000

Data Index: 77099 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.7351. Min Act: -0.0000

Data Index: 323970 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.7024. Min Act: -0.0000

Data Index: 1643151 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.5993. Min Act: -0.0000

Data Index: 501440 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 2.4011. Min Range: -2.4011

Max Act: 1.6900. Min Act: -0.0000

Data Index: 1062813 (C4 (Web Text))

Max Activating Token Index: 609