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

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

Neuron 1318 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: 3.5936. Min Range: -3.5936

Max Act: 3.5936. Min Act: -0.1700

Data Index: 800030 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.5455. Min Act: -0.1700

Data Index: 74189 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.4609. Min Act: -0.1700

Data Index: 1143445 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.4092. Min Act: -0.1700

Data Index: 467382 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.4237. Min Act: -0.1700

Data Index: 831445 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.3578. Min Act: -0.1700

Data Index: 426546 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.3583. Min Act: -0.1700

Data Index: 453113 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.3639. Min Act: -0.1700

Data Index: 198203 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.3470. Min Act: -0.1700

Data Index: 394881 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.2927. Min Act: -0.1700

Data Index: 873185 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.3019. Min Act: -0.1700

Data Index: 256597 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.2679. Min Act: -0.1700

Data Index: 774403 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.2429. Min Act: -0.1700

Data Index: 1332743 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.2465. Min Act: -0.1700

Data Index: 304873 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.2569. Min Act: -0.1700

Data Index: 563830 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.2631. Min Act: -0.1700

Data Index: 1245283 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.2445. Min Act: -0.1700

Data Index: 1154886 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.2487. Min Act: -0.1699

Data Index: 269613 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.2296. Min Act: -0.1700

Data Index: 1541184 (Python Code)

Max Activating Token Index: 683

Text #19

Max Range: 3.5936. Min Range: -3.5936

Max Act: 3.2314. Min Act: -0.1700

Data Index: 1641668 (Python Code)

Max Activating Token Index: 909