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

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

Neuron 371 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: 5.8786. Min Range: -5.8786

Max Act: 5.8786. Min Act: -0.1700

Data Index: 689664 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.8474. Min Act: -0.1700

Data Index: 390747 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.6911. Min Act: -0.1700

Data Index: 33579 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.6911. Min Act: -0.1700

Data Index: 39479 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.5661. Min Act: -0.1700

Data Index: 1325520 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.5661. Min Act: -0.1700

Data Index: 449161 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.5349. Min Act: -0.1700

Data Index: 89221 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.5661. Min Act: -0.1700

Data Index: 217935 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.4411. Min Act: -0.1700

Data Index: 1253780 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.5349. Min Act: -0.1700

Data Index: 1322141 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.5036. Min Act: -0.1700

Data Index: 61949 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.5036. Min Act: -0.1700

Data Index: 1115075 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.5036. Min Act: -0.1700

Data Index: 767729 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.4724. Min Act: -0.1700

Data Index: 771957 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.4411. Min Act: -0.1700

Data Index: 1341710 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.4411. Min Act: -0.1700

Data Index: 426884 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.4099. Min Act: -0.1700

Data Index: 1157202 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.4099. Min Act: -0.1700

Data Index: 128564 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.3786. Min Act: -0.1700

Data Index: 88499 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 5.8786. Min Range: -5.8786

Max Act: 5.4099. Min Act: -0.1700

Data Index: 950706 (C4 (Web Text))

Max Activating Token Index: 998