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

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

Neuron 286 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: 3.6614. Min Range: -3.6614

Max Act: 3.6614. Min Act: -0.1700

Data Index: 397192 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.5048. Min Act: -0.1700

Data Index: 204223 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.3950. Min Act: -0.1700

Data Index: 725305 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.3480. Min Act: -0.1700

Data Index: 447741 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.3166. Min Act: -0.1700

Data Index: 1566913 (Python Code)

Max Activating Token Index: 1021

Text #5

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2694. Min Act: -0.1700

Data Index: 736768 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.3009. Min Act: -0.1700

Data Index: 402810 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2852. Min Act: -0.1700

Data Index: 826794 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2537. Min Act: -0.1700

Data Index: 601292 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2852. Min Act: -0.1700

Data Index: 775259 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2694. Min Act: -0.1700

Data Index: 370310 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2537. Min Act: -0.1700

Data Index: 1166606 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2380. Min Act: -0.1700

Data Index: 42514 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2223. Min Act: -0.1700

Data Index: 1081215 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2223. Min Act: -0.1700

Data Index: 202949 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2380. Min Act: -0.1700

Data Index: 222162 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2066. Min Act: -0.1700

Data Index: 216275 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2066. Min Act: -0.1700

Data Index: 972371 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2066. Min Act: -0.1700

Data Index: 607560 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 3.6614. Min Range: -3.6614

Max Act: 3.2066. Min Act: -0.1700

Data Index: 322988 (C4 (Web Text))

Max Activating Token Index: 200