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

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

Neuron 1301 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: 4.0356. Min Range: -4.0356

Max Act: 4.0356. Min Act: -0.1700

Data Index: 1308389 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 4.0356. Min Range: -4.0356

Max Act: 4.0356. Min Act: -0.1700

Data Index: 290755 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 4.0356. Min Range: -4.0356

Max Act: 4.0043. Min Act: -0.1700

Data Index: 624047 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 4.0356. Min Range: -4.0356

Max Act: 4.0043. Min Act: -0.1700

Data Index: 1124820 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 4.0356. Min Range: -4.0356

Max Act: 4.0043. Min Act: -0.1700

Data Index: 969402 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 4.0356. Min Range: -4.0356

Max Act: 4.0043. Min Act: -0.1700

Data Index: 114691 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9731. Min Act: -0.1700

Data Index: 854557 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9418. Min Act: -0.1700

Data Index: 852456 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9731. Min Act: -0.1700

Data Index: 734222 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9418. Min Act: -0.1700

Data Index: 88057 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9418. Min Act: -0.1700

Data Index: 391109 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9418. Min Act: -0.1700

Data Index: 71027 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9418. Min Act: -0.1700

Data Index: 633686 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9105. Min Act: -0.1700

Data Index: 1029160 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9105. Min Act: -0.1700

Data Index: 554137 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9418. Min Act: -0.1700

Data Index: 1044096 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9105. Min Act: -0.1700

Data Index: 468350 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9731. Min Act: -0.1700

Data Index: 1228700 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9105. Min Act: -0.1700

Data Index: 905238 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9105. Min Act: -0.1700

Data Index: 205887 (C4 (Web Text))

Max Activating Token Index: 654