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

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

Neuron 3196 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1522. Min Act: -0.0000

Data Index: 671360 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1106630 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1459. Min Act: -0.0001

Data Index: 395268 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1202. Min Act: -0.0000

Data Index: 906412 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1236544 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1231. Min Act: -0.0001

Data Index: 326968 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1281. Min Act: -0.0000

Data Index: 144953 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1112. Min Act: -0.0000

Data Index: 744005 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1353742 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1231. Min Act: -0.0000

Data Index: 89163 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1066. Min Act: -0.0000

Data Index: 909840 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1104. Min Act: -0.0000

Data Index: 759957 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1084. Min Act: -0.0000

Data Index: 156347 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1204888 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1105. Min Act: -0.0000

Data Index: 911794 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1237121 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1059. Min Act: -0.0000

Data Index: 155092 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0990. Min Act: -0.0000

Data Index: 641294 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1245039 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1060601 (C4 (Web Text))

Max Activating Token Index: 583