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

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

Neuron 2039 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: 4.2762. Min Range: -4.2762

Max Act: 4.2762. Min Act: -0.1700

Data Index: 676628 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.2450. Min Act: -0.1700

Data Index: 1095804 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1824. Min Act: -0.1700

Data Index: 1142207 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1512. Min Act: -0.1700

Data Index: 456509 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1512. Min Act: -0.1700

Data Index: 464737 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1199. Min Act: -0.1700

Data Index: 592305 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1199. Min Act: -0.1700

Data Index: 617389 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1199. Min Act: -0.1700

Data Index: 335321 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0887. Min Act: -0.1700

Data Index: 437296 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0574. Min Act: -0.1700

Data Index: 716439 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0887. Min Act: -0.1700

Data Index: 920960 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0887. Min Act: -0.1700

Data Index: 941959 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1199. Min Act: -0.1700

Data Index: 277788 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0887. Min Act: -0.1700

Data Index: 1003368 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0574. Min Act: -0.1700

Data Index: 623358 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0574. Min Act: -0.1700

Data Index: 333790 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0574. Min Act: -0.1700

Data Index: 48384 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0574. Min Act: -0.1700

Data Index: 249774 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0261. Min Act: -0.1700

Data Index: 644150 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.0574. Min Act: -0.1700

Data Index: 657480 (C4 (Web Text))

Max Activating Token Index: 859