Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 396 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1361. Min Act: -0.0005

Data Index: 189199 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1258. Min Act: -0.0005

Data Index: 17565 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1218. Min Act: -0.0005

Data Index: 131745 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1158. Min Act: -0.0005

Data Index: 185899 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1146. Min Act: -0.0005

Data Index: 120524 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1097. Min Act: -0.0005

Data Index: 1304459 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1087. Min Act: -0.0005

Data Index: 1047566 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1009. Min Act: -0.0005

Data Index: 64191 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1037. Min Act: -0.0005

Data Index: 780077 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0994. Min Act: -0.0005

Data Index: 359017 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1026. Min Act: -0.0005

Data Index: 188914 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1024. Min Act: -0.0005

Data Index: 1150194 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1019. Min Act: -0.0005

Data Index: 524389 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0979. Min Act: -0.0005

Data Index: 929304 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1016. Min Act: -0.0005

Data Index: 602024 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1006. Min Act: -0.0005

Data Index: 692080 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0956. Min Act: -0.0005

Data Index: 271710 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1031. Min Act: -0.0005

Data Index: 867017 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0950. Min Act: -0.0005

Data Index: 1334238 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1020. Min Act: -0.0005

Data Index: 1232467 (C4 (Web Text))

Max Activating Token Index: 861