Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 948 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1073547 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1028245 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1386. Min Act: -0.0001

Data Index: 136441 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1141. Min Act: -0.0001

Data Index: 630666 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1020400 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1077332 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1100. Min Act: -0.0001

Data Index: 937449 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1112. Min Act: -0.0001

Data Index: 825255 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1062. Min Act: -0.0001

Data Index: 521239 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0986. Min Act: -0.0001

Data Index: 470036 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1054. Min Act: -0.0001

Data Index: 735843 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1090. Min Act: -0.0001

Data Index: 905701 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1136. Min Act: -0.0001

Data Index: 660829 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0967. Min Act: -0.0001

Data Index: 643222 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0993. Min Act: -0.0001

Data Index: 104072 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0933. Min Act: -0.0001

Data Index: 843321 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1047. Min Act: -0.0001

Data Index: 950684 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1043. Min Act: -0.0001

Data Index: 938889 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1004. Min Act: -0.0001

Data Index: 747880 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1004. Min Act: -0.0001

Data Index: 491700 (C4 (Web Text))

Max Activating Token Index: 541