Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1406 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.2031. Min Act: -0.1700

Data Index: 1280943 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.2189. Min Act: -0.1700

Data Index: 847471 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.1402. Min Act: -0.1700

Data Index: 864153 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.0929. Min Act: -0.1700

Data Index: 471338 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.0771. Min Act: -0.1700

Data Index: 347765 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.0456. Min Act: -0.1700

Data Index: 1004561 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.0456. Min Act: -0.1700

Data Index: 119056 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.0298. Min Act: -0.1700

Data Index: 1191468 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.1087. Min Act: -0.1700

Data Index: 1254244 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.0140. Min Act: -0.1700

Data Index: 257617 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.0140. Min Act: -0.1700

Data Index: 876651 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.0456. Min Act: -0.1698

Data Index: 545766 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 3.2189. Min Range: -3.2189

Max Act: 3.0456. Min Act: -0.1700

Data Index: 1201913 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 3.2189. Min Range: -3.2189

Max Act: 2.9982. Min Act: -0.1700

Data Index: 847228 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 3.2189. Min Range: -3.2189

Max Act: 2.9507. Min Act: -0.1700

Data Index: 644237 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 3.2189. Min Range: -3.2189

Max Act: 2.9982. Min Act: -0.1700

Data Index: 444382 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 3.2189. Min Range: -3.2189

Max Act: 2.9507. Min Act: -0.1699

Data Index: 550013 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 3.2189. Min Range: -3.2189

Max Act: 2.9665. Min Act: -0.1700

Data Index: 71633 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 3.2189. Min Range: -3.2189

Max Act: 2.9823. Min Act: -0.1700

Data Index: 807935 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 3.2189. Min Range: -3.2189

Max Act: 2.9665. Min Act: -0.1700

Data Index: 536568 (C4 (Web Text))

Max Activating Token Index: 325