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

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

Neuron 4103 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0001

Data Index: 234705 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1124. Min Act: -0.0001

Data Index: 814677 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0916. Min Act: -0.0001

Data Index: 49974 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1171373 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1498316 (Python Code)

Max Activating Token Index: 183

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0875. Min Act: -0.0000

Data Index: 847169 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0807. Min Act: -0.0001

Data Index: 366304 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0804. Min Act: -0.0001

Data Index: 527582 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0842. Min Act: -0.0000

Data Index: 18878 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0839. Min Act: -0.0001

Data Index: 110213 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0885. Min Act: -0.0001

Data Index: 92140 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1519605 (Python Code)

Max Activating Token Index: 482

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1316472 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0842. Min Act: -0.0001

Data Index: 896554 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0787. Min Act: -0.0001

Data Index: 588893 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1363116 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1599685 (Python Code)

Max Activating Token Index: 870

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0885. Min Act: -0.0001

Data Index: 279142 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0779. Min Act: -0.0001

Data Index: 482569 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0802. Min Act: -0.0001

Data Index: 1261090 (C4 (Web Text))

Max Activating Token Index: 336