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

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

Neuron 113 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: 3.4956. Min Range: -3.4956

Max Act: 3.4956. Min Act: -0.1700

Data Index: 1034330 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.4016. Min Act: -0.1700

Data Index: 1146327 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.3702. Min Act: -0.1700

Data Index: 1293400 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.3388. Min Act: -0.1700

Data Index: 698673 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.3388. Min Act: -0.1700

Data Index: 136670 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.3388. Min Act: -0.1700

Data Index: 939713 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.3231. Min Act: -0.1700

Data Index: 982694 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2917. Min Act: -0.1700

Data Index: 126843 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.3074. Min Act: -0.1700

Data Index: 902861 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2760. Min Act: -0.1700

Data Index: 1331966 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2917. Min Act: -0.1700

Data Index: 1301089 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2760. Min Act: -0.1700

Data Index: 734314 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2760. Min Act: -0.1700

Data Index: 488527 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2917. Min Act: -0.1700

Data Index: 100982 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2603. Min Act: -0.1700

Data Index: 1079375 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2603. Min Act: -0.1700

Data Index: 385790 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2603. Min Act: -0.1700

Data Index: 128507 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2603. Min Act: -0.1700

Data Index: 1355518 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2760. Min Act: -0.1700

Data Index: 1135008 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 3.4956. Min Range: -3.4956

Max Act: 3.2603. Min Act: -0.1700

Data Index: 641371 (C4 (Web Text))

Max Activating Token Index: 614