Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1540 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8991. Min Act: -0.0001

Data Index: 1485933 (Python Code)

Max Activating Token Index: 436

Text #1

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8645. Min Act: -0.0001

Data Index: 1393546 (Python Code)

Max Activating Token Index: 617

Text #2

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6803. Min Act: -0.0001

Data Index: 1514693 (Python Code)

Max Activating Token Index: 147

Text #3

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6946. Min Act: -0.0001

Data Index: 1581912 (Python Code)

Max Activating Token Index: 891

Text #4

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6238. Min Act: -0.0001

Data Index: 1570037 (Python Code)

Max Activating Token Index: 184

Text #5

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6958. Min Act: -0.0001

Data Index: 1534857 (Python Code)

Max Activating Token Index: 146

Text #6

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7163. Min Act: -0.0001

Data Index: 1449840 (Python Code)

Max Activating Token Index: 658

Text #7

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6669. Min Act: -0.0001

Data Index: 1436493 (Python Code)

Max Activating Token Index: 949

Text #8

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6796. Min Act: -0.0001

Data Index: 1532664 (Python Code)

Max Activating Token Index: 194

Text #9

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6378. Min Act: -0.0001

Data Index: 1464427 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5873. Min Act: -0.0001

Data Index: 1440215 (Python Code)

Max Activating Token Index: 620

Text #11

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6043. Min Act: -0.0001

Data Index: 1385999 (Python Code)

Max Activating Token Index: 903

Text #12

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6039. Min Act: -0.0001

Data Index: 1619221 (Python Code)

Max Activating Token Index: 269

Text #13

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6547. Min Act: -0.0001

Data Index: 1476721 (Python Code)

Max Activating Token Index: 891

Text #14

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5939. Min Act: -0.0001

Data Index: 1460219 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5525. Min Act: -0.0001

Data Index: 1608451 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6325. Min Act: -0.0001

Data Index: 1572472 (Python Code)

Max Activating Token Index: 333

Text #17

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6107. Min Act: -0.0001

Data Index: 1577675 (Python Code)

Max Activating Token Index: 767

Text #18

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1565353 (Python Code)

Max Activating Token Index: 225

Text #19

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6127. Min Act: -0.0001

Data Index: 1432451 (Python Code)

Max Activating Token Index: 122