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

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

Neuron 1050 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: 0.1522. Min Range: -0.1522

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1480877 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1497925 (Python Code)

Max Activating Token Index: 52

Text #2

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1584393 (Python Code)

Max Activating Token Index: 54

Text #3

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1555616 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1654985 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1374903 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1399904 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1628815 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1626696 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1139. Min Act: -0.0000

Data Index: 599261 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1547450 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1483842 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1163. Min Act: -0.0000

Data Index: 1397561 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1630212 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1148. Min Act: -0.0000

Data Index: 836106 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1378879 (Python Code)

Max Activating Token Index: 40

Text #16

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1605179 (Python Code)

Max Activating Token Index: 46

Text #17

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1137. Min Act: -0.0000

Data Index: 659095 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1093. Min Act: -0.0000

Data Index: 44097 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.1522. Min Range: -0.1522

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1639603 (Python Code)

Max Activating Token Index: 11