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

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

Neuron 3492 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6035. Min Range: -1.6035

Max Act: 1.6035. Min Act: -0.0000

Data Index: 440594 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 1.6035. Min Range: -1.6035

Max Act: 1.1944. Min Act: -0.0000

Data Index: 519325 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 1.6035. Min Range: -1.6035

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1209259 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 1.6035. Min Range: -1.6035

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1343884 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1067168 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.6035. Min Range: -1.6035

Max Act: 1.0333. Min Act: -0.0000

Data Index: 924076 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.9956. Min Act: -0.0000

Data Index: 771268 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.9527. Min Act: -0.0000

Data Index: 802566 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1240909 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 1.6035. Min Range: -1.6035

Max Act: 1.0223. Min Act: -0.0000

Data Index: 1234234 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.9090. Min Act: -0.0000

Data Index: 606593 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.9361. Min Act: -0.0000

Data Index: 381744 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.9014. Min Act: -0.0000

Data Index: 664520 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.8478. Min Act: -0.0000

Data Index: 1014606 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1157121 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.8802. Min Act: -0.0000

Data Index: 158914 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1243082 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.8555. Min Act: -0.0000

Data Index: 711132 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1213608 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.6035. Min Range: -1.6035

Max Act: 0.7952. Min Act: -0.0000

Data Index: 268123 (C4 (Web Text))

Max Activating Token Index: 358