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

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

Neuron 501 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4098. Min Range: -5.4098

Max Act: 5.4098. Min Act: -0.1700

Data Index: 488193 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 5.4098. Min Range: -5.4098

Max Act: 5.2536. Min Act: -0.1700

Data Index: 742300 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 5.4098. Min Range: -5.4098

Max Act: 5.0973. Min Act: -0.1700

Data Index: 252225 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 5.4098. Min Range: -5.4098

Max Act: 5.0661. Min Act: -0.1700

Data Index: 1290174 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 5.4098. Min Range: -5.4098

Max Act: 5.0348. Min Act: -0.1700

Data Index: 1171707 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 5.4098. Min Range: -5.4098

Max Act: 5.0348. Min Act: -0.1700

Data Index: 973825 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 5.4098. Min Range: -5.4098

Max Act: 4.9723. Min Act: -0.1700

Data Index: 426248 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 5.4098. Min Range: -5.4098

Max Act: 4.9411. Min Act: -0.1700

Data Index: 426768 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 5.4098. Min Range: -5.4098

Max Act: 5.0036. Min Act: -0.1700

Data Index: 1115950 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 5.4098. Min Range: -5.4098

Max Act: 5.0348. Min Act: -0.1700

Data Index: 627709 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 5.4098. Min Range: -5.4098

Max Act: 5.0036. Min Act: -0.1700

Data Index: 224438 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 5.4098. Min Range: -5.4098

Max Act: 5.0036. Min Act: -0.1700

Data Index: 803351 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 5.4098. Min Range: -5.4098

Max Act: 4.9411. Min Act: -0.1700

Data Index: 1350639 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 5.4098. Min Range: -5.4098

Max Act: 4.9098. Min Act: -0.1700

Data Index: 452628 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 5.4098. Min Range: -5.4098

Max Act: 4.8786. Min Act: -0.1700

Data Index: 1224622 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 5.4098. Min Range: -5.4098

Max Act: 4.8473. Min Act: -0.1700

Data Index: 1106045 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 5.4098. Min Range: -5.4098

Max Act: 4.8473. Min Act: -0.1700

Data Index: 902613 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 5.4098. Min Range: -5.4098

Max Act: 4.9411. Min Act: -0.1700

Data Index: 460567 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 5.4098. Min Range: -5.4098

Max Act: 4.9411. Min Act: -0.1700

Data Index: 327811 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 5.4098. Min Range: -5.4098

Max Act: 4.8786. Min Act: -0.1700

Data Index: 396148 (C4 (Web Text))

Max Activating Token Index: 794