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

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

Neuron 191 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: 3.4883. Min Range: -3.4883

Max Act: 3.4883. Min Act: -0.1700

Data Index: 870609 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3815. Min Act: -0.1700

Data Index: 354945 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.4029. Min Act: -0.1700

Data Index: 1026195 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3681. Min Act: -0.1700

Data Index: 273333 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1270 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3683. Min Act: -0.1700

Data Index: 942496 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3375. Min Act: -0.1700

Data Index: 150881 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3791. Min Act: -0.1700

Data Index: 1238745 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3429. Min Act: -0.1700

Data Index: 148585 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3164. Min Act: -0.1700

Data Index: 321861 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3490. Min Act: -0.1700

Data Index: 903545 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3454. Min Act: -0.1700

Data Index: 92988 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3475. Min Act: -0.1700

Data Index: 380711 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3463. Min Act: -0.1700

Data Index: 1078583 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3364. Min Act: -0.1700

Data Index: 244509 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3303. Min Act: -0.1700

Data Index: 922153 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3119. Min Act: -0.1700

Data Index: 523998 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3275. Min Act: -0.1700

Data Index: 1329099 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.2965. Min Act: -0.1700

Data Index: 880861 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3132. Min Act: -0.1700

Data Index: 515944 (C4 (Web Text))

Max Activating Token Index: 233