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

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

Neuron 1117 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: 0.1458. Min Range: -0.1458

Max Act: 0.1347. Min Act: -0.0000

Data Index: 850967 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1458. Min Act: -0.0000

Data Index: 82927 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1270. Min Act: -0.0000

Data Index: 784411 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1133. Min Act: -0.0001

Data Index: 922430 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1131494 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1079. Min Act: -0.0001

Data Index: 278830 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1102. Min Act: -0.0000

Data Index: 326008 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1058. Min Act: -0.0001

Data Index: 620338 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1157347 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1356471 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0986. Min Act: -0.0001

Data Index: 549395 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0994. Min Act: -0.0000

Data Index: 780612 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0904. Min Act: -0.0001

Data Index: 12841 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1212555 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1444517 (Python Code)

Max Activating Token Index: 845

Text #15

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1282594 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0923. Min Act: -0.0000

Data Index: 521058 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0857. Min Act: -0.0000

Data Index: 722125 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0879. Min Act: -0.0000

Data Index: 143894 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1231084 (C4 (Web Text))

Max Activating Token Index: 553