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

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

Neuron 1903 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.4046. Min Act: -0.1700

Data Index: 1271774 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3419. Min Act: -0.1700

Data Index: 580038 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3262. Min Act: -0.1700

Data Index: 243745 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3105. Min Act: -0.1700

Data Index: 211406 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2948. Min Act: -0.1700

Data Index: 870312 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2476. Min Act: -0.1700

Data Index: 442761 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2476. Min Act: -0.1700

Data Index: 1355813 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2476. Min Act: -0.1700

Data Index: 952821 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2634. Min Act: -0.1700

Data Index: 443316 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2162. Min Act: -0.1700

Data Index: 1085190 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2005. Min Act: -0.1700

Data Index: 797614 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.1690. Min Act: -0.1700

Data Index: 1241985 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.1690. Min Act: -0.1700

Data Index: 481741 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.1690. Min Act: -0.1700

Data Index: 278004 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.1375. Min Act: -0.1700

Data Index: 804421 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.1375. Min Act: -0.1700

Data Index: 358020 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.1375. Min Act: -0.1700

Data Index: 135866 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.1375. Min Act: -0.1700

Data Index: 943354 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.1060. Min Act: -0.1700

Data Index: 791904 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.1217. Min Act: -0.1700

Data Index: 1003721 (C4 (Web Text))

Max Activating Token Index: 664