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

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

Neuron 477 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.6079. Min Act: -0.1700

Data Index: 1135696 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3414. Min Act: -0.1700

Data Index: 912367 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.4042. Min Act: -0.1700

Data Index: 1273086 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3728. Min Act: -0.1700

Data Index: 1323462 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3571. Min Act: -0.1700

Data Index: 79944 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3728. Min Act: -0.1700

Data Index: 821028 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3414. Min Act: -0.1700

Data Index: 99648 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3414. Min Act: -0.1700

Data Index: 68178 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.2943. Min Act: -0.1700

Data Index: 192332 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3571. Min Act: -0.1700

Data Index: 555714 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3257. Min Act: -0.1700

Data Index: 1192974 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.3100. Min Act: -0.1700

Data Index: 1158733 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.2943. Min Act: -0.1700

Data Index: 1157627 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.2786. Min Act: -0.1700

Data Index: 260460 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.2943. Min Act: -0.1700

Data Index: 906668 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.2943. Min Act: -0.1700

Data Index: 738812 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.2786. Min Act: -0.1700

Data Index: 73364 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.2314. Min Act: -0.1700

Data Index: 967912 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.2629. Min Act: -0.1700

Data Index: 271906 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 3.6079. Min Range: -3.6079

Max Act: 3.2314. Min Act: -0.1700

Data Index: 1015922 (C4 (Web Text))

Max Activating Token Index: 80