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

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

Neuron 895 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: 4.0206. Min Range: -4.0206

Max Act: 4.0206. Min Act: -0.1700

Data Index: 1575048 (Python Code)

Max Activating Token Index: 397

Text #1

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.9728. Min Act: -0.1700

Data Index: 1381192 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.9488. Min Act: -0.1700

Data Index: 1477674 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.9123. Min Act: -0.1700

Data Index: 1651480 (Python Code)

Max Activating Token Index: 387

Text #4

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.8955. Min Act: -0.1700

Data Index: 1515037 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.8652. Min Act: -0.1700

Data Index: 1455232 (Python Code)

Max Activating Token Index: 602

Text #6

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.8478. Min Act: -0.1700

Data Index: 1605320 (Python Code)

Max Activating Token Index: 161

Text #7

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.8549. Min Act: -0.1700

Data Index: 1362472 (Python Code)

Max Activating Token Index: 622

Text #8

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.8223. Min Act: -0.1700

Data Index: 1396065 (Python Code)

Max Activating Token Index: 341

Text #9

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.8325. Min Act: -0.1700

Data Index: 1465384 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.7932. Min Act: -0.1700

Data Index: 1607549 (Python Code)

Max Activating Token Index: 110

Text #11

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.8067. Min Act: -0.1700

Data Index: 1361108 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.7865. Min Act: -0.1700

Data Index: 1462412 (Python Code)

Max Activating Token Index: 655

Text #13

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.7942. Min Act: -0.1700

Data Index: 1610562 (Python Code)

Max Activating Token Index: 880

Text #14

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.7526. Min Act: -0.1700

Data Index: 1451343 (Python Code)

Max Activating Token Index: 785

Text #15

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.7705. Min Act: -0.1700

Data Index: 1573956 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.8056. Min Act: -0.1700

Data Index: 1618767 (Python Code)

Max Activating Token Index: 548

Text #17

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.7468. Min Act: -0.1700

Data Index: 1519473 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.7800. Min Act: -0.1700

Data Index: 1567733 (Python Code)

Max Activating Token Index: 956

Text #19

Max Range: 4.0206. Min Range: -4.0206

Max Act: 3.7200. Min Act: -0.1700

Data Index: 1362187 (Python Code)

Max Activating Token Index: 654