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

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

Neuron 2103 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1691. Min Act: -0.0002

Data Index: 1226189 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1731. Min Act: -0.0002

Data Index: 347428 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1930. Min Act: -0.0002

Data Index: 329315 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1932. Min Act: -0.0002

Data Index: 1171140 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1502. Min Act: -0.0002

Data Index: 574405 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1720. Min Act: -0.0002

Data Index: 889109 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1486. Min Act: -0.0002

Data Index: 1226978 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1351. Min Act: -0.0002

Data Index: 640549 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1489. Min Act: -0.0002

Data Index: 1180494 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1567. Min Act: -0.0002

Data Index: 719431 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1480. Min Act: -0.0002

Data Index: 1109062 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1301. Min Act: -0.0002

Data Index: 668989 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1446. Min Act: -0.0002

Data Index: 541458 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1289. Min Act: -0.0002

Data Index: 441991 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1528. Min Act: -0.0002

Data Index: 171449 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1312. Min Act: -0.0002

Data Index: 836090 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1522. Min Act: -0.0002

Data Index: 1354364 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1175. Min Act: -0.0002

Data Index: 333726 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1305004 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1325. Min Act: -0.0002

Data Index: 135078 (C4 (Web Text))

Max Activating Token Index: 330