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

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

Neuron 1792 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1302. Min Act: -0.0002

Data Index: 946628 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1252. Min Act: -0.0002

Data Index: 361242 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1235. Min Act: -0.0002

Data Index: 219971 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1157. Min Act: -0.0002

Data Index: 1202157 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1247551 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1178317 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1095. Min Act: -0.0002

Data Index: 892901 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1003785 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0992. Min Act: -0.0002

Data Index: 875561 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0946. Min Act: -0.0002

Data Index: 987907 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1101373 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0945. Min Act: -0.0002

Data Index: 292610 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0939. Min Act: -0.0002

Data Index: 243025 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0945. Min Act: -0.0002

Data Index: 521098 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1075802 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1168236 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1092720 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0895. Min Act: -0.0002

Data Index: 940279 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0924. Min Act: -0.0002

Data Index: 503196 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0853. Min Act: -0.0002

Data Index: 922059 (C4 (Web Text))

Max Activating Token Index: 710