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

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

Neuron 1349 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: 3.5547. Min Range: -3.5547

Max Act: 3.5547. Min Act: -0.1700

Data Index: 34094 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.3980. Min Act: -0.1700

Data Index: 1031984 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.3666. Min Act: -0.1700

Data Index: 1151559 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.3352. Min Act: -0.1700

Data Index: 1013181 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.3980. Min Act: -0.1700

Data Index: 883194 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.3666. Min Act: -0.1700

Data Index: 250464 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2724. Min Act: -0.1700

Data Index: 125835 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2724. Min Act: -0.1700

Data Index: 1208846 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2881. Min Act: -0.1700

Data Index: 854146 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.3038. Min Act: -0.1700

Data Index: 247355 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.3352. Min Act: -0.1700

Data Index: 1197403 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2881. Min Act: -0.1700

Data Index: 613736 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.3038. Min Act: -0.1700

Data Index: 525790 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2724. Min Act: -0.1700

Data Index: 554224 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2409. Min Act: -0.1700

Data Index: 764610 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2567. Min Act: -0.1700

Data Index: 512150 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2252. Min Act: -0.1700

Data Index: 507968 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2409. Min Act: -0.1700

Data Index: 1110903 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2409. Min Act: -0.1700

Data Index: 115235 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 3.5547. Min Range: -3.5547

Max Act: 3.2252. Min Act: -0.1700

Data Index: 712486 (C4 (Web Text))

Max Activating Token Index: 683