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

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

Neuron 251 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: 2.0185. Min Range: -2.0185

Max Act: 2.0185. Min Act: -0.0000

Data Index: 379153 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.7648. Min Act: -0.0000

Data Index: 579989 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1283952 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.6270. Min Act: -0.0000

Data Index: 98954 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.6577. Min Act: -0.0000

Data Index: 1293643 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.5629. Min Act: -0.0000

Data Index: 1400419 (Python Code)

Max Activating Token Index: 987

Text #6

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.5211. Min Act: -0.0000

Data Index: 1040610 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.6763. Min Act: -0.0000

Data Index: 872824 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.4367. Min Act: -0.0000

Data Index: 501227 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.5126. Min Act: -0.0000

Data Index: 1153804 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.4362. Min Act: -0.0000

Data Index: 1229121 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.4141. Min Act: -0.0000

Data Index: 242812 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.4201. Min Act: -0.0000

Data Index: 731000 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.4990. Min Act: -0.0000

Data Index: 1643899 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1553317 (Python Code)

Max Activating Token Index: 567

Text #15

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.4354. Min Act: -0.0000

Data Index: 1142921 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.4023. Min Act: -0.0000

Data Index: 481665 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.4966. Min Act: -0.0000

Data Index: 645460 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.4435. Min Act: -0.0000

Data Index: 1583745 (Python Code)

Max Activating Token Index: 448

Text #19

Max Range: 2.0185. Min Range: -2.0185

Max Act: 1.3993. Min Act: -0.0000

Data Index: 883355 (C4 (Web Text))

Max Activating Token Index: 13