Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 91 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.6560. Min Act: -0.1700

Data Index: 1119023 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.5310. Min Act: -0.1700

Data Index: 395479 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.5622. Min Act: -0.1700

Data Index: 1327729 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.5935. Min Act: -0.1700

Data Index: 244848 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.4997. Min Act: -0.1700

Data Index: 799900 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.4372. Min Act: -0.1700

Data Index: 498163 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.4372. Min Act: -0.1700

Data Index: 392206 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.4372. Min Act: -0.1700

Data Index: 236559 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.3747. Min Act: -0.1700

Data Index: 517569 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.3122. Min Act: -0.1700

Data Index: 1152960 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.4060. Min Act: -0.1700

Data Index: 755848 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.3122. Min Act: -0.1700

Data Index: 62873 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.2810. Min Act: -0.1700

Data Index: 26640 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.2185. Min Act: -0.1700

Data Index: 1197859 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.2810. Min Act: -0.1699

Data Index: 1140817 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.2497. Min Act: -0.1700

Data Index: 1060612 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.2497. Min Act: -0.1700

Data Index: 503190 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.2185. Min Act: -0.1700

Data Index: 857505 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.2185. Min Act: -0.1700

Data Index: 454700 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 5.6560. Min Range: -5.6560

Max Act: 5.1872. Min Act: -0.1700

Data Index: 1080773 (C4 (Web Text))

Max Activating Token Index: 444