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

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

Neuron 1952 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: 4.0980. Min Range: -4.0980

Max Act: 4.0980. Min Act: -0.1700

Data Index: 584817 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 4.0980. Min Range: -4.0980

Max Act: 4.0518. Min Act: -0.1700

Data Index: 18943 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.9863. Min Act: -0.1700

Data Index: 1195297 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.9724. Min Act: -0.1700

Data Index: 190029 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.9282. Min Act: -0.1700

Data Index: 478909 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.9083. Min Act: -0.1699

Data Index: 1269912 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8848. Min Act: -0.1700

Data Index: 443565 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8621. Min Act: -0.1699

Data Index: 978500 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8824. Min Act: -0.1700

Data Index: 474384 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8726. Min Act: -0.1700

Data Index: 334851 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8578. Min Act: -0.1700

Data Index: 1226498 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8373. Min Act: -0.1700

Data Index: 180716 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8410. Min Act: -0.1700

Data Index: 831783 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8391. Min Act: -0.1700

Data Index: 826007 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8341. Min Act: -0.1700

Data Index: 362769 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8380. Min Act: -0.1700

Data Index: 1085083 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8102. Min Act: -0.1700

Data Index: 985983 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8015. Min Act: -0.1700

Data Index: 688376 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8136. Min Act: -0.1700

Data Index: 773876 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 4.0980. Min Range: -4.0980

Max Act: 3.8099. Min Act: -0.1700

Data Index: 850051 (C4 (Web Text))

Max Activating Token Index: 706