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

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

Neuron 971 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: 3.5064. Min Range: -3.5064

Max Act: 3.5064. Min Act: -0.1700

Data Index: 988329 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.4014. Min Act: -0.1700

Data Index: 252278 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.4040. Min Act: -0.1700

Data Index: 492500 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.3870. Min Act: -0.1700

Data Index: 771382 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1243840 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.3681. Min Act: -0.1700

Data Index: 650895 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.3756. Min Act: -0.1700

Data Index: 303023 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.3515. Min Act: -0.1700

Data Index: 865821 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.3284. Min Act: -0.1700

Data Index: 323606 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.3256. Min Act: -0.1700

Data Index: 812153 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.2950. Min Act: -0.1700

Data Index: 183534 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.2976. Min Act: -0.1700

Data Index: 1156183 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.2659. Min Act: -0.1700

Data Index: 358441 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.2537. Min Act: -0.1700

Data Index: 1222810 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.2410. Min Act: -0.1700

Data Index: 380078 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.2309. Min Act: -0.1700

Data Index: 418124 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.2587. Min Act: -0.1700

Data Index: 460689 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.2428. Min Act: -0.1700

Data Index: 7411 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.2108. Min Act: -0.1700

Data Index: 1142181 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 3.5064. Min Range: -3.5064

Max Act: 3.2359. Min Act: -0.1700

Data Index: 649172 (C4 (Web Text))

Max Activating Token Index: 237