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

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

Neuron 1749 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.3895. Min Act: -0.1700

Data Index: 611873 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.3895. Min Act: -0.1700

Data Index: 1072569 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.4208. Min Act: -0.1700

Data Index: 133688 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.3895. Min Act: -0.1700

Data Index: 551893 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.3895. Min Act: -0.1700

Data Index: 661887 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.3895. Min Act: -0.1700

Data Index: 336372 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.3583. Min Act: -0.1700

Data Index: 1043179 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.3270. Min Act: -0.1700

Data Index: 1185214 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.3270. Min Act: -0.1700

Data Index: 703070 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.3583. Min Act: -0.1700

Data Index: 265902 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.2645. Min Act: -0.1700

Data Index: 349185 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.3270. Min Act: -0.1700

Data Index: 1220223 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.2645. Min Act: -0.1700

Data Index: 808025 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.2645. Min Act: -0.1700

Data Index: 202146 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.2958. Min Act: -0.1700

Data Index: 1329232 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.2958. Min Act: -0.1700

Data Index: 316297 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.2645. Min Act: -0.1700

Data Index: 77768 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.2645. Min Act: -0.1700

Data Index: 1125441 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.2645. Min Act: -0.1700

Data Index: 379593 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 5.4208. Min Range: -5.4208

Max Act: 5.2645. Min Act: -0.1700

Data Index: 974889 (C4 (Web Text))

Max Activating Token Index: 608