Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1548 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.2952. Min Act: -0.1699

Data Index: 1170161 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.3169. Min Act: -0.1690

Data Index: 1516541 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.2344. Min Act: -0.1700

Data Index: 220105 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.2056. Min Act: -0.1700

Data Index: 1444050 (Python Code)

Max Activating Token Index: 760

Text #4

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.2186. Min Act: -0.1700

Data Index: 451182 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1858. Min Act: -0.1700

Data Index: 181444 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1990. Min Act: -0.1349

Data Index: 1362287 (Python Code)

Max Activating Token Index: 288

Text #7

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1928. Min Act: -0.1349

Data Index: 1645719 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1487. Min Act: -0.1349

Data Index: 1422288 (Python Code)

Max Activating Token Index: 584

Text #9

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1368. Min Act: -0.1349

Data Index: 1507948 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1612. Min Act: -0.1349

Data Index: 1470459 (Python Code)

Max Activating Token Index: 868

Text #11

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1539. Min Act: -0.1349

Data Index: 1633858 (Python Code)

Max Activating Token Index: 622

Text #12

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1443. Min Act: -0.1696

Data Index: 1582165 (Python Code)

Max Activating Token Index: 927

Text #13

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1268. Min Act: -0.1349

Data Index: 1537625 (Python Code)

Max Activating Token Index: 566

Text #14

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1216. Min Act: -0.1349

Data Index: 1651403 (Python Code)

Max Activating Token Index: 908

Text #15

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1128. Min Act: -0.1652

Data Index: 1538691 (Python Code)

Max Activating Token Index: 173

Text #16

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1222. Min Act: -0.1700

Data Index: 1419582 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1218. Min Act: -0.1349

Data Index: 1615758 (Python Code)

Max Activating Token Index: 433

Text #18

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1109. Min Act: -0.1669

Data Index: 1629147 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 3.3169. Min Range: -3.3169

Max Act: 3.1358. Min Act: -0.1349

Data Index: 1562023 (Python Code)

Max Activating Token Index: 203