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

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

Neuron 1666 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: 7.8276. Min Range: -7.8276

Max Act: 7.7026. Min Act: -0.1700

Data Index: 1138771 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.8276. Min Act: -0.1700

Data Index: 1258586 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.6401. Min Act: -0.1700

Data Index: 1278476 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.7026. Min Act: -0.1700

Data Index: 913883 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.7651. Min Act: -0.1700

Data Index: 1322285 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.7026. Min Act: -0.1700

Data Index: 525344 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.7026. Min Act: -0.1700

Data Index: 533002 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.6401. Min Act: -0.1700

Data Index: 1260469 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.5776. Min Act: -0.1700

Data Index: 222650 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.6401. Min Act: -0.1700

Data Index: 1186337 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.5151. Min Act: -0.1700

Data Index: 1344188 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.5151. Min Act: -0.1700

Data Index: 374881 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.5151. Min Act: -0.1700

Data Index: 764521 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.5151. Min Act: -0.1700

Data Index: 756759 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.5151. Min Act: -0.1700

Data Index: 1242750 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.5151. Min Act: -0.1700

Data Index: 1243159 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.5151. Min Act: -0.1700

Data Index: 681225 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.4526. Min Act: -0.1699

Data Index: 208980 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.4526. Min Act: -0.1700

Data Index: 403351 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 7.8276. Min Range: -7.8276

Max Act: 7.4526. Min Act: -0.1700

Data Index: 324498 (C4 (Web Text))

Max Activating Token Index: 182