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

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

Neuron 1505 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.8624. Min Act: -0.1700

Data Index: 1114777 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.8311. Min Act: -0.1700

Data Index: 905700 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7998. Min Act: -0.1700

Data Index: 1289475 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7685. Min Act: -0.1700

Data Index: 1025377 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7685. Min Act: -0.1700

Data Index: 815701 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.8311. Min Act: -0.1700

Data Index: 440898 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7685. Min Act: -0.1700

Data Index: 408444 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7372. Min Act: -0.1700

Data Index: 91442 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7372. Min Act: -0.1700

Data Index: 1042910 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7372. Min Act: -0.1700

Data Index: 1110442 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7059. Min Act: -0.1700

Data Index: 1116161 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7059. Min Act: -0.1700

Data Index: 897979 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7059. Min Act: -0.1700

Data Index: 39203 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7372. Min Act: -0.1700

Data Index: 917085 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7372. Min Act: -0.1700

Data Index: 181708 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7059. Min Act: -0.1700

Data Index: 788674 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.6746. Min Act: -0.1700

Data Index: 220645 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7059. Min Act: -0.1700

Data Index: 1293409 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.7372. Min Act: -0.1700

Data Index: 1315172 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 3.8624. Min Range: -3.8624

Max Act: 3.6746. Min Act: -0.1700

Data Index: 535271 (C4 (Web Text))

Max Activating Token Index: 182