Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 742 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.4064. Min Act: -0.1700

Data Index: 1195867 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.3907. Min Act: -0.1700

Data Index: 110479 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.3593. Min Act: -0.1700

Data Index: 593304 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.3593. Min Act: -0.1700

Data Index: 1068549 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.3279. Min Act: -0.1700

Data Index: 184149 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.3279. Min Act: -0.1700

Data Index: 217269 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.3279. Min Act: -0.1700

Data Index: 679419 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.3122. Min Act: -0.1699

Data Index: 852520 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2965. Min Act: -0.1700

Data Index: 396464 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2965. Min Act: -0.1700

Data Index: 488199 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2965. Min Act: -0.1700

Data Index: 459 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2651. Min Act: -0.1700

Data Index: 1293206 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2965. Min Act: -0.1700

Data Index: 2556 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2808. Min Act: -0.1700

Data Index: 977874 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2808. Min Act: -0.1700

Data Index: 165302 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2494. Min Act: -0.1700

Data Index: 482706 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2651. Min Act: -0.1700

Data Index: 930276 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2651. Min Act: -0.1700

Data Index: 244485 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2494. Min Act: -0.1700

Data Index: 515527 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.2494. Min Act: -0.1700

Data Index: 273449 (C4 (Web Text))

Max Activating Token Index: 614