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

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

Neuron 266 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.7038. Min Act: -0.1700

Data Index: 1038067 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6725. Min Act: -0.1700

Data Index: 913593 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6568. Min Act: -0.1700

Data Index: 1116943 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6725. Min Act: -0.1700

Data Index: 1050289 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6725. Min Act: -0.1700

Data Index: 138290 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6725. Min Act: -0.1700

Data Index: 526774 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6725. Min Act: -0.1700

Data Index: 1346355 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6568. Min Act: -0.1700

Data Index: 1071791 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6412. Min Act: -0.1700

Data Index: 152044 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6255. Min Act: -0.1700

Data Index: 160569 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6255. Min Act: -0.1700

Data Index: 695127 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6255. Min Act: -0.1700

Data Index: 387979 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6255. Min Act: -0.1700

Data Index: 988334 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6412. Min Act: -0.1700

Data Index: 207617 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6098. Min Act: -0.1700

Data Index: 117739 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6255. Min Act: -0.1700

Data Index: 1193668 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6255. Min Act: -0.1700

Data Index: 639019 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6255. Min Act: -0.1700

Data Index: 1257680 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6098. Min Act: -0.1700

Data Index: 160568 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 3.7038. Min Range: -3.7038

Max Act: 3.6255. Min Act: -0.1700

Data Index: 1332404 (C4 (Web Text))

Max Activating Token Index: 229