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

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

Neuron 3546 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1483994 (Python Code)

Max Activating Token Index: 392

Text #1

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.4011. Min Act: -0.0000

Data Index: 147 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.1682. Min Act: -0.0000

Data Index: 50227 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.1631. Min Act: -0.0000

Data Index: 333873 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1365276 (Python Code)

Max Activating Token Index: 473

Text #5

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.0372. Min Act: -0.0000

Data Index: 1123232 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.0670. Min Act: -0.0000

Data Index: 1009310 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.1336. Min Act: -0.0000

Data Index: 393195 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1586314 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1168204 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 1.4011. Min Range: -1.4011

Max Act: 0.9977. Min Act: -0.0000

Data Index: 678009 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.0282. Min Act: -0.0000

Data Index: 790968 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.0488. Min Act: -0.0000

Data Index: 1146556 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.4011. Min Range: -1.4011

Max Act: 0.9689. Min Act: -0.0000

Data Index: 506928 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 1.4011. Min Range: -1.4011

Max Act: 0.9957. Min Act: -0.0000

Data Index: 293061 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.4011. Min Range: -1.4011

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1307666 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 1.4011. Min Range: -1.4011

Max Act: 0.8630. Min Act: -0.0000

Data Index: 748128 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 1.4011. Min Range: -1.4011

Max Act: 1.0091. Min Act: -0.0000

Data Index: 672476 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 1.4011. Min Range: -1.4011

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1099283 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 1.4011. Min Range: -1.4011

Max Act: 0.9992. Min Act: -0.0000

Data Index: 320455 (C4 (Web Text))

Max Activating Token Index: 443