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

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

Neuron 2670 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1632. Min Act: -0.0000

Data Index: 249085 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1547. Min Act: -0.0000

Data Index: 474401 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1463. Min Act: -0.0000

Data Index: 10648 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1444. Min Act: -0.0000

Data Index: 820868 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1300482 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1515. Min Act: -0.0000

Data Index: 763016 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1364. Min Act: -0.0000

Data Index: 105632 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1431. Min Act: -0.0000

Data Index: 989044 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1281958 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1258. Min Act: -0.0000

Data Index: 470559 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1062554 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1263. Min Act: -0.0000

Data Index: 311584 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1207. Min Act: -0.0000

Data Index: 28010 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1107662 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1164. Min Act: -0.0000

Data Index: 528426 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1180. Min Act: -0.0000

Data Index: 734145 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1217. Min Act: -0.0000

Data Index: 959139 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1254292 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1168. Min Act: -0.0000

Data Index: 140322 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1255. Min Act: -0.0000

Data Index: 535479 (C4 (Web Text))

Max Activating Token Index: 932