Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 757 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.6073. Min Act: -0.1700

Data Index: 106459 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.5916. Min Act: -0.1700

Data Index: 1292909 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.5290. Min Act: -0.1700

Data Index: 693015 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.5133. Min Act: -0.1700

Data Index: 481949 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.4663. Min Act: -0.1700

Data Index: 127326 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.4820. Min Act: -0.1700

Data Index: 343260 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.4663. Min Act: -0.1700

Data Index: 971937 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.4506. Min Act: -0.1700

Data Index: 562145 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.4349. Min Act: -0.1700

Data Index: 379300 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.4192. Min Act: -0.1700

Data Index: 883200 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.4192. Min Act: -0.1700

Data Index: 899150 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.4036. Min Act: -0.1700

Data Index: 349481 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.3879. Min Act: -0.1700

Data Index: 819654 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.3722. Min Act: -0.1700

Data Index: 334072 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.3722. Min Act: -0.1700

Data Index: 1154865 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.3408. Min Act: -0.1700

Data Index: 619527 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.3408. Min Act: -0.1700

Data Index: 1119374 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.3408. Min Act: -0.1700

Data Index: 1000602 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.3408. Min Act: -0.1700

Data Index: 742966 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 3.6073. Min Range: -3.6073

Max Act: 3.3251. Min Act: -0.1700

Data Index: 611306 (C4 (Web Text))

Max Activating Token Index: 105