Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 659 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.5729. Min Act: -0.1700

Data Index: 1098912 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.5693. Min Act: -0.1700

Data Index: 1077234 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.5786. Min Act: -0.1700

Data Index: 674963 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.5617. Min Act: -0.1700

Data Index: 724741 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.5500. Min Act: -0.1700

Data Index: 1162421 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.4959. Min Act: -0.1700

Data Index: 756722 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.4787. Min Act: -0.1700

Data Index: 372466 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.5013. Min Act: -0.1700

Data Index: 104657 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.4420. Min Act: -0.1700

Data Index: 11213 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.4987. Min Act: -0.1700

Data Index: 964948 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.4664. Min Act: -0.1700

Data Index: 891850 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.4652. Min Act: -0.1700

Data Index: 1091865 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.4449. Min Act: -0.1700

Data Index: 1459135 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.4257. Min Act: -0.1700

Data Index: 677965 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.4078. Min Act: -0.1700

Data Index: 823565 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.3942. Min Act: -0.1700

Data Index: 1180803 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.4060. Min Act: -0.1700

Data Index: 1326654 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.3486. Min Act: -0.1700

Data Index: 252489 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.3930. Min Act: -0.1700

Data Index: 908938 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.3712. Min Act: -0.1700

Data Index: 54812 (C4 (Web Text))

Max Activating Token Index: 807