Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 884 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.3942. Min Act: -0.1700

Data Index: 1128349 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2215. Min Act: -0.1700

Data Index: 1053548 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2372. Min Act: -0.1700

Data Index: 985387 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2372. Min Act: -0.1700

Data Index: 1025192 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1900. Min Act: -0.1700

Data Index: 1217415 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2057. Min Act: -0.1700

Data Index: 689481 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1743. Min Act: -0.1700

Data Index: 934567 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1585. Min Act: -0.1700

Data Index: 365436 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1585. Min Act: -0.1700

Data Index: 834475 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1428. Min Act: -0.1700

Data Index: 1177315 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1428. Min Act: -0.1700

Data Index: 39449 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1270. Min Act: -0.1700

Data Index: 1148853 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1428. Min Act: -0.1700

Data Index: 167732 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1113. Min Act: -0.1700

Data Index: 1357831 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1113. Min Act: -0.1700

Data Index: 420871 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1113. Min Act: -0.1700

Data Index: 641077 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1270. Min Act: -0.1700

Data Index: 461021 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1270. Min Act: -0.1700

Data Index: 799107 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1113. Min Act: -0.1700

Data Index: 21557 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.0955. Min Act: -0.1700

Data Index: 339102 (C4 (Web Text))

Max Activating Token Index: 883