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

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

Neuron 1964 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: 4.7629. Min Range: -4.7629

Max Act: 4.7629. Min Act: -0.1700

Data Index: 1094355 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.7559. Min Act: -0.1700

Data Index: 891486 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.6943. Min Act: -0.1700

Data Index: 380967 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.5214. Min Act: -0.1700

Data Index: 906434 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.5227. Min Act: -0.1700

Data Index: 938358 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.5349. Min Act: -0.1700

Data Index: 1202011 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.4990. Min Act: -0.1700

Data Index: 461629 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.4615. Min Act: -0.1700

Data Index: 428621 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.4664. Min Act: -0.1700

Data Index: 740343 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.4491. Min Act: -0.1696

Data Index: 442924 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.4278. Min Act: -0.1699

Data Index: 303948 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.4144. Min Act: -0.1700

Data Index: 765973 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.4014. Min Act: -0.1700

Data Index: 1107146 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.4131. Min Act: -0.1700

Data Index: 279616 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.3497. Min Act: -0.1700

Data Index: 1116152 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.3723. Min Act: -0.1700

Data Index: 518579 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.3855. Min Act: -0.1700

Data Index: 1176318 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.3916. Min Act: -0.1700

Data Index: 723085 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.3875. Min Act: -0.1700

Data Index: 291615 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 4.7629. Min Range: -4.7629

Max Act: 4.3945. Min Act: -0.1700

Data Index: 644164 (C4 (Web Text))

Max Activating Token Index: 130