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

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

Neuron 673 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: 3.5926. Min Range: -3.5926

Max Act: 3.5926. Min Act: -0.1700

Data Index: 1554164 (Python Code)

Max Activating Token Index: 110

Text #1

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.4242. Min Act: -0.1698

Data Index: 1406028 (Python Code)

Max Activating Token Index: 318

Text #2

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.2981. Min Act: -0.1700

Data Index: 1389592 (Python Code)

Max Activating Token Index: 595

Text #3

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.2976. Min Act: -0.1699

Data Index: 1561697 (Python Code)

Max Activating Token Index: 616

Text #4

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.2941. Min Act: -0.1688

Data Index: 1484757 (Python Code)

Max Activating Token Index: 186

Text #5

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.2791. Min Act: -0.1700

Data Index: 1375629 (Python Code)

Max Activating Token Index: 48

Text #6

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.2357. Min Act: -0.1700

Data Index: 1590550 (Python Code)

Max Activating Token Index: 243

Text #7

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.1910. Min Act: -0.1700

Data Index: 839535 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.1284. Min Act: -0.1700

Data Index: 1350753 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.1309. Min Act: -0.1700

Data Index: 1216781 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.1274. Min Act: -0.1700

Data Index: 613513 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.1100. Min Act: -0.1699

Data Index: 646987 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.1320. Min Act: -0.1698

Data Index: 1605612 (Python Code)

Max Activating Token Index: 144

Text #13

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.1052. Min Act: -0.1700

Data Index: 1519086 (Python Code)

Max Activating Token Index: 110

Text #14

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.1146. Min Act: -0.1698

Data Index: 1555210 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.0923. Min Act: -0.1688

Data Index: 1561070 (Python Code)

Max Activating Token Index: 568

Text #16

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.0906. Min Act: -0.1699

Data Index: 1364095 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.0767. Min Act: -0.1699

Data Index: 1557053 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.0737. Min Act: -0.1699

Data Index: 814869 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 3.5926. Min Range: -3.5926

Max Act: 3.0528. Min Act: -0.1700

Data Index: 1394964 (Python Code)

Max Activating Token Index: 962