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

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

Neuron 651 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.7064. Min Act: -0.0001

Data Index: 1595037 (Python Code)

Max Activating Token Index: 478

Text #1

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5852. Min Act: -0.0001

Data Index: 1470137 (Python Code)

Max Activating Token Index: 129

Text #2

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.6705. Min Act: -0.0001

Data Index: 1394586 (Python Code)

Max Activating Token Index: 549

Text #3

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.6589. Min Act: -0.0001

Data Index: 1637170 (Python Code)

Max Activating Token Index: 604

Text #4

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5987. Min Act: -0.0001

Data Index: 1429171 (Python Code)

Max Activating Token Index: 88

Text #5

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5097. Min Act: -0.0001

Data Index: 1511756 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5052. Min Act: -0.0001

Data Index: 67732 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5340. Min Act: -0.0001

Data Index: 1375776 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5288. Min Act: -0.0001

Data Index: 1319984 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5376. Min Act: -0.0001

Data Index: 1527956 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5289. Min Act: -0.0001

Data Index: 1419813 (Python Code)

Max Activating Token Index: 384

Text #11

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4948. Min Act: -0.0001

Data Index: 1443373 (Python Code)

Max Activating Token Index: 671

Text #12

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.6024. Min Act: -0.0001

Data Index: 1383813 (Python Code)

Max Activating Token Index: 931

Text #13

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5011. Min Act: -0.0001

Data Index: 1438707 (Python Code)

Max Activating Token Index: 584

Text #14

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5075. Min Act: -0.0001

Data Index: 1534984 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4662. Min Act: -0.0001

Data Index: 1506142 (Python Code)

Max Activating Token Index: 929

Text #16

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4689. Min Act: -0.0001

Data Index: 390200 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4797. Min Act: -0.0001

Data Index: 1515072 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4935. Min Act: -0.0001

Data Index: 1531686 (Python Code)

Max Activating Token Index: 362

Text #19

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4803. Min Act: -0.0001

Data Index: 1638029 (Python Code)

Max Activating Token Index: 86