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

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

Neuron 178 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: 3.9630. Min Range: -3.9630

Max Act: 3.9630. Min Act: -0.1700

Data Index: 148173 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.9562. Min Act: -0.1700

Data Index: 1124746 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.8375. Min Act: -0.1700

Data Index: 1170362 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1385808 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.8279. Min Act: -0.1700

Data Index: 276291 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7912. Min Act: -0.1700

Data Index: 825104 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7688. Min Act: -0.1700

Data Index: 1427037 (Python Code)

Max Activating Token Index: 300

Text #7

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7478. Min Act: -0.1700

Data Index: 398569 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7640. Min Act: -0.1700

Data Index: 1463486 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7523. Min Act: -0.1700

Data Index: 1453983 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7381. Min Act: -0.1700

Data Index: 1464081 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7435. Min Act: -0.1700

Data Index: 1125376 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7359. Min Act: -0.1700

Data Index: 547710 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7076. Min Act: -0.1700

Data Index: 1635344 (Python Code)

Max Activating Token Index: 193

Text #14

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7104. Min Act: -0.1700

Data Index: 99692 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7344. Min Act: -0.1700

Data Index: 483222 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7172. Min Act: -0.1700

Data Index: 917465 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7235. Min Act: -0.1700

Data Index: 829907 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.6817. Min Act: -0.1700

Data Index: 619039 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 3.9630. Min Range: -3.9630

Max Act: 3.7023. Min Act: -0.1700

Data Index: 673167 (C4 (Web Text))

Max Activating Token Index: 758