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

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

Neuron 3106 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: 0.1758. Min Range: -0.1758

Max Act: 0.1758. Min Act: -0.0001

Data Index: 980142 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1571. Min Act: -0.0001

Data Index: 704643 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1548. Min Act: -0.0001

Data Index: 638921 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1523. Min Act: -0.0001

Data Index: 585350 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1494. Min Act: -0.0001

Data Index: 824149 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1454. Min Act: -0.0001

Data Index: 4923 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1280. Min Act: -0.0001

Data Index: 673476 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1335. Min Act: -0.0001

Data Index: 276507 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1371. Min Act: -0.0001

Data Index: 524522 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1301. Min Act: -0.0001

Data Index: 23610 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1339. Min Act: -0.0001

Data Index: 399640 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1102665 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1350. Min Act: -0.0001

Data Index: 704143 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1278. Min Act: -0.0001

Data Index: 253607 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1186. Min Act: -0.0001

Data Index: 225771 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1015174 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1297. Min Act: -0.0001

Data Index: 884513 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1256. Min Act: -0.0001

Data Index: 356680 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1309. Min Act: -0.0001

Data Index: 107339 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1293. Min Act: -0.0001

Data Index: 782483 (C4 (Web Text))

Max Activating Token Index: 22