Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 606 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.9954. Min Act: -0.1700

Data Index: 576129 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.9741. Min Act: -0.1700

Data Index: 798698 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.9710. Min Act: -0.1700

Data Index: 510685 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.9493. Min Act: -0.1700

Data Index: 127155 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.9562. Min Act: -0.1700

Data Index: 1099227 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.9361. Min Act: -0.1700

Data Index: 952224 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.9491. Min Act: -0.1700

Data Index: 1194883 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.9111. Min Act: -0.1700

Data Index: 893363 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.9075. Min Act: -0.1700

Data Index: 1325870 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8974. Min Act: -0.1700

Data Index: 509225 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8721. Min Act: -0.1700

Data Index: 1105972 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8758. Min Act: -0.1700

Data Index: 125002 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8708. Min Act: -0.1700

Data Index: 309568 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8717. Min Act: -0.1700

Data Index: 343885 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8848. Min Act: -0.1700

Data Index: 851744 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8823. Min Act: -0.1700

Data Index: 1241163 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8845. Min Act: -0.1699

Data Index: 489157 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8903. Min Act: -0.1700

Data Index: 265006 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8329. Min Act: -0.1700

Data Index: 129133 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 2.9954. Min Range: -2.9954

Max Act: 2.8374. Min Act: -0.1700

Data Index: 1073979 (C4 (Web Text))

Max Activating Token Index: 923