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

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

Neuron 1254 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.5305. Min Act: -0.1700

Data Index: 236709 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.5148. Min Act: -0.1700

Data Index: 998141 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.4835. Min Act: -0.1700

Data Index: 230752 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.4521. Min Act: -0.1700

Data Index: 533307 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.4208. Min Act: -0.1700

Data Index: 936837 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.4364. Min Act: -0.1700

Data Index: 1311078 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3894. Min Act: -0.1700

Data Index: 686529 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3109. Min Act: -0.1700

Data Index: 352970 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3580. Min Act: -0.1700

Data Index: 814247 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3580. Min Act: -0.1700

Data Index: 1177381 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3737. Min Act: -0.1700

Data Index: 151752 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3423. Min Act: -0.1700

Data Index: 736708 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3580. Min Act: -0.1700

Data Index: 1257852 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3109. Min Act: -0.1700

Data Index: 112109 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3266. Min Act: -0.1700

Data Index: 414592 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3266. Min Act: -0.1700

Data Index: 407899 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.2638. Min Act: -0.1700

Data Index: 18390 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3109. Min Act: -0.1700

Data Index: 328068 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.3109. Min Act: -0.1700

Data Index: 182910 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 3.5305. Min Range: -3.5305

Max Act: 3.2952. Min Act: -0.1700

Data Index: 383795 (C4 (Web Text))

Max Activating Token Index: 52