Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 580 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.3297. Min Act: -0.1700

Data Index: 1349705 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.3140. Min Act: -0.1700

Data Index: 229774 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2983. Min Act: -0.1700

Data Index: 462545 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2983. Min Act: -0.1700

Data Index: 614457 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2826. Min Act: -0.1700

Data Index: 1343730 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2983. Min Act: -0.1700

Data Index: 231200 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2669. Min Act: -0.1700

Data Index: 211486 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2669. Min Act: -0.1700

Data Index: 837518 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2669. Min Act: -0.1700

Data Index: 153924 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2511. Min Act: -0.1700

Data Index: 968715 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2511. Min Act: -0.1700

Data Index: 1302599 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2354. Min Act: -0.1700

Data Index: 67180 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2511. Min Act: -0.1700

Data Index: 414841 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2197. Min Act: -0.1700

Data Index: 253654 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2354. Min Act: -0.1700

Data Index: 1325702 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2197. Min Act: -0.1700

Data Index: 277185 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2197. Min Act: -0.1700

Data Index: 494045 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2197. Min Act: -0.1700

Data Index: 697641 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2197. Min Act: -0.1700

Data Index: 1144916 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2197. Min Act: -0.1700

Data Index: 1070288 (C4 (Web Text))

Max Activating Token Index: 725