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

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

Neuron 1412 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: 3.6517. Min Range: -3.6517

Max Act: 3.6517. Min Act: -0.1700

Data Index: 144937 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.5578. Min Act: -0.1700

Data Index: 693555 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.5108. Min Act: -0.1700

Data Index: 1333306 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.4951. Min Act: -0.1700

Data Index: 989827 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.4795. Min Act: -0.1700

Data Index: 37476 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.4324. Min Act: -0.1700

Data Index: 714449 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.4011. Min Act: -0.1700

Data Index: 905199 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.3854. Min Act: -0.1700

Data Index: 22827 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.4011. Min Act: -0.1700

Data Index: 558915 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.4168. Min Act: -0.1700

Data Index: 195302 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.3540. Min Act: -0.1700

Data Index: 754528 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.4011. Min Act: -0.1700

Data Index: 1156329 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.4011. Min Act: -0.1700

Data Index: 1242767 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.3854. Min Act: -0.1700

Data Index: 404596 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.3383. Min Act: -0.1700

Data Index: 1003140 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.3540. Min Act: -0.1700

Data Index: 1165789 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.3383. Min Act: -0.1700

Data Index: 308840 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.3226. Min Act: -0.1700

Data Index: 1211748 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.3383. Min Act: -0.1700

Data Index: 557539 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.3069. Min Act: -0.1700

Data Index: 849413 (C4 (Web Text))

Max Activating Token Index: 348