Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2050 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1215. Min Act: -0.0001

Data Index: 303996 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1240. Min Act: -0.0001

Data Index: 443347 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1298. Min Act: -0.0001

Data Index: 795154 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1199. Min Act: -0.0001

Data Index: 180351 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1258. Min Act: -0.0001

Data Index: 637542 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1106. Min Act: -0.0001

Data Index: 367817 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1056. Min Act: -0.0001

Data Index: 651325 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1126. Min Act: -0.0001

Data Index: 328119 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1023. Min Act: -0.0001

Data Index: 4823 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1073. Min Act: -0.0001

Data Index: 424206 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1085. Min Act: -0.0001

Data Index: 409395 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1274887 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1098. Min Act: -0.0001

Data Index: 747090 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0916. Min Act: -0.0001

Data Index: 474680 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0933. Min Act: -0.0001

Data Index: 728214 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0969. Min Act: -0.0001

Data Index: 335991 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0966. Min Act: -0.0001

Data Index: 83958 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1143883 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0921. Min Act: -0.0001

Data Index: 895042 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1125306 (C4 (Web Text))

Max Activating Token Index: 90