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

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

Neuron 987 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1057. Min Range: -5.1057

Max Act: 5.1057. Min Act: -0.1700

Data Index: 555025 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 5.1057. Min Range: -5.1057

Max Act: 5.0745. Min Act: -0.1699

Data Index: 1180413 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 5.1057. Min Range: -5.1057

Max Act: 5.0432. Min Act: -0.1700

Data Index: 1213864 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 5.1057. Min Range: -5.1057

Max Act: 5.0120. Min Act: -0.1699

Data Index: 1018712 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 5.1057. Min Range: -5.1057

Max Act: 5.0432. Min Act: -0.1700

Data Index: 458085 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 5.1057. Min Range: -5.1057

Max Act: 5.0120. Min Act: -0.1700

Data Index: 158263 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 5.1057. Min Range: -5.1057

Max Act: 5.0120. Min Act: -0.1700

Data Index: 417899 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 5.1057. Min Range: -5.1057

Max Act: 5.0120. Min Act: -0.1700

Data Index: 32667 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.9495. Min Act: -0.1699

Data Index: 47265 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.9807. Min Act: -0.1700

Data Index: 82278 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.9807. Min Act: -0.1700

Data Index: 783932 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.8870. Min Act: -0.1700

Data Index: 1159803 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.9182. Min Act: -0.1700

Data Index: 148295 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.8870. Min Act: -0.1700

Data Index: 809877 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.8870. Min Act: -0.1700

Data Index: 687631 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.8870. Min Act: -0.1700

Data Index: 832646 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.8245. Min Act: -0.1700

Data Index: 1091088 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.8557. Min Act: -0.1700

Data Index: 226957 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.8557. Min Act: -0.1700

Data Index: 1118939 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 5.1057. Min Range: -5.1057

Max Act: 4.8870. Min Act: -0.1700

Data Index: 275319 (C4 (Web Text))

Max Activating Token Index: 496