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

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

Neuron 1118 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2414. Min Range: -5.2414

Max Act: 5.2414. Min Act: -0.1700

Data Index: 523865 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.8976. Min Act: -0.1700

Data Index: 457385 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.7726. Min Act: -0.1700

Data Index: 644380 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.8038. Min Act: -0.1700

Data Index: 262393 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.7413. Min Act: -0.1700

Data Index: 1119170 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.7101. Min Act: -0.1700

Data Index: 300532 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.7101. Min Act: -0.1700

Data Index: 274522 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.6163. Min Act: -0.1700

Data Index: 1316874 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.6788. Min Act: -0.1700

Data Index: 458282 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.6163. Min Act: -0.1700

Data Index: 378923 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.5851. Min Act: -0.1700

Data Index: 504420 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.7101. Min Act: -0.1700

Data Index: 831915 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.6163. Min Act: -0.1700

Data Index: 33958 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.5851. Min Act: -0.1700

Data Index: 459732 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.5851. Min Act: -0.1700

Data Index: 470262 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.5226. Min Act: -0.1700

Data Index: 768602 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.6163. Min Act: -0.1700

Data Index: 412818 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.5538. Min Act: -0.1700

Data Index: 170416 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.5538. Min Act: -0.1700

Data Index: 225145 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 5.2414. Min Range: -5.2414

Max Act: 4.5851. Min Act: -0.1700

Data Index: 108575 (C4 (Web Text))

Max Activating Token Index: 73