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

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

Neuron 2326 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4369. Min Range: -2.4369

Max Act: 2.4369. Min Act: -0.0000

Data Index: 1369907 (Python Code)

Max Activating Token Index: 602

Text #1

Max Range: 2.4369. Min Range: -2.4369

Max Act: 2.2510. Min Act: -0.0000

Data Index: 1528060 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 2.4369. Min Range: -2.4369

Max Act: 2.0877. Min Act: -0.0000

Data Index: 1596492 (Python Code)

Max Activating Token Index: 695

Text #3

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.8090. Min Act: -0.0000

Data Index: 1613127 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.9994. Min Act: -0.0000

Data Index: 1365790 (Python Code)

Max Activating Token Index: 317

Text #5

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.9542. Min Act: -0.0000

Data Index: 1623936 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.9641. Min Act: -0.0000

Data Index: 1627403 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.9268. Min Act: -0.0000

Data Index: 1489925 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.8135. Min Act: -0.0000

Data Index: 1394950 (Python Code)

Max Activating Token Index: 972

Text #9

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.8352. Min Act: -0.0000

Data Index: 1502506 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.7902. Min Act: -0.0000

Data Index: 1571963 (Python Code)

Max Activating Token Index: 992

Text #11

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.6990. Min Act: -0.0000

Data Index: 1558352 (Python Code)

Max Activating Token Index: 461

Text #12

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.7964. Min Act: -0.0000

Data Index: 1479538 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.7811. Min Act: -0.0000

Data Index: 1124948 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.7049. Min Act: -0.0000

Data Index: 1650400 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.6767. Min Act: -0.0000

Data Index: 1458378 (Python Code)

Max Activating Token Index: 278

Text #16

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.8140. Min Act: -0.0000

Data Index: 1401055 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1271456 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.6023. Min Act: -0.0000

Data Index: 1441231 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 2.4369. Min Range: -2.4369

Max Act: 1.6502. Min Act: -0.0000

Data Index: 1638035 (Python Code)

Max Activating Token Index: 4