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

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

Neuron 1384 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: 3.5879. Min Range: -3.5879

Max Act: 3.5879. Min Act: -0.1700

Data Index: 475750 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.4463. Min Act: -0.1700

Data Index: 1237838 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.4644. Min Act: -0.1700

Data Index: 845491 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.4053. Min Act: -0.1700

Data Index: 1509360 (Python Code)

Max Activating Token Index: 322

Text #4

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.4200. Min Act: -0.1700

Data Index: 293237 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.4025. Min Act: -0.1700

Data Index: 235534 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3880. Min Act: -0.1700

Data Index: 1538024 (Python Code)

Max Activating Token Index: 371

Text #7

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3948. Min Act: -0.1700

Data Index: 303749 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3485. Min Act: -0.1700

Data Index: 1440323 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3449. Min Act: -0.1700

Data Index: 299320 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3720. Min Act: -0.1700

Data Index: 482786 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3890. Min Act: -0.1700

Data Index: 351912 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3366. Min Act: -0.1700

Data Index: 12104 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3557. Min Act: -0.1700

Data Index: 964510 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3465. Min Act: -0.1700

Data Index: 787585 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3323. Min Act: -0.1700

Data Index: 1555951 (Python Code)

Max Activating Token Index: 684

Text #16

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3186. Min Act: -0.1700

Data Index: 473551 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3271. Min Act: -0.1700

Data Index: 508365 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3507. Min Act: -0.1700

Data Index: 377748 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 3.5879. Min Range: -3.5879

Max Act: 3.3081. Min Act: -0.1700

Data Index: 1394596 (Python Code)

Max Activating Token Index: 392