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

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

Neuron 1499 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1782. Min Range: -5.1782

Max Act: 5.1782. Min Act: -0.1700

Data Index: 246379 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 5.1782. Min Range: -5.1782

Max Act: 5.1157. Min Act: -0.1700

Data Index: 1221325 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 5.1782. Min Range: -5.1782

Max Act: 5.0844. Min Act: -0.1700

Data Index: 576037 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 5.1782. Min Range: -5.1782

Max Act: 5.0844. Min Act: -0.1700

Data Index: 633458 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 5.1782. Min Range: -5.1782

Max Act: 5.0219. Min Act: -0.1700

Data Index: 782368 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 5.1782. Min Range: -5.1782

Max Act: 5.0532. Min Act: -0.1700

Data Index: 1067146 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.9907. Min Act: -0.1700

Data Index: 440665 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.9907. Min Act: -0.1700

Data Index: 451558 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.9594. Min Act: -0.1700

Data Index: 407273 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.8969. Min Act: -0.1700

Data Index: 567999 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.9907. Min Act: -0.1699

Data Index: 128498 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.9594. Min Act: -0.1700

Data Index: 153799 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.9907. Min Act: -0.1700

Data Index: 274409 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.9594. Min Act: -0.1700

Data Index: 279221 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.9594. Min Act: -0.1700

Data Index: 826725 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.8657. Min Act: -0.1700

Data Index: 700565 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.8657. Min Act: -0.1700

Data Index: 1131548 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.8969. Min Act: -0.1700

Data Index: 604553 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.8344. Min Act: -0.1700

Data Index: 1079550 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 5.1782. Min Range: -5.1782

Max Act: 4.8969. Min Act: -0.1700

Data Index: 830361 (C4 (Web Text))

Max Activating Token Index: 609