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

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

Neuron 274 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0722. Min Range: -4.0722

Max Act: 4.0722. Min Act: -0.1700

Data Index: 63412 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.9784. Min Act: -0.1700

Data Index: 479693 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.9784. Min Act: -0.1700

Data Index: 631089 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.9628. Min Act: -0.1700

Data Index: 809245 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.9315. Min Act: -0.1700

Data Index: 166645 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.9002. Min Act: -0.1700

Data Index: 876569 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.8377. Min Act: -0.1700

Data Index: 205657 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.8064. Min Act: -0.1700

Data Index: 96972 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.7751. Min Act: -0.1700

Data Index: 438708 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.7595. Min Act: -0.1700

Data Index: 764486 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.7595. Min Act: -0.1700

Data Index: 9964 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.7595. Min Act: -0.1700

Data Index: 398684 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.7282. Min Act: -0.1700

Data Index: 94302 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.7438. Min Act: -0.1700

Data Index: 919984 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.7125. Min Act: -0.1700

Data Index: 1314651 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.6656. Min Act: -0.1700

Data Index: 513662 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.4150. Min Act: -0.1700

Data Index: 1100412 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.3993. Min Act: -0.1700

Data Index: 1432408 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.3836. Min Act: -0.1700

Data Index: 1186311 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 4.0722. Min Range: -4.0722

Max Act: 3.3993. Min Act: -0.1700

Data Index: 1220074 (C4 (Web Text))

Max Activating Token Index: 464