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

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

Neuron 184 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: 4.2588. Min Range: -4.2588

Max Act: 4.2588. Min Act: -0.1700

Data Index: 978913 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 4.2588. Min Range: -4.2588

Max Act: 4.1826. Min Act: -0.1700

Data Index: 379514 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 4.2588. Min Range: -4.2588

Max Act: 4.1619. Min Act: -0.1700

Data Index: 1163249 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 4.2588. Min Range: -4.2588

Max Act: 4.1228. Min Act: -0.1700

Data Index: 229266 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 4.2588. Min Range: -4.2588

Max Act: 4.0900. Min Act: -0.1700

Data Index: 1217151 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 4.2588. Min Range: -4.2588

Max Act: 4.0605. Min Act: -0.1700

Data Index: 505891 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 4.2588. Min Range: -4.2588

Max Act: 4.0476. Min Act: -0.1700

Data Index: 251922 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 4.2588. Min Range: -4.2588

Max Act: 4.0273. Min Act: -0.1700

Data Index: 202681 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 4.2588. Min Range: -4.2588

Max Act: 4.0031. Min Act: -0.1700

Data Index: 1284116 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 4.2588. Min Range: -4.2588

Max Act: 4.0100. Min Act: -0.1700

Data Index: 46274 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 4.2588. Min Range: -4.2588

Max Act: 3.9900. Min Act: -0.1700

Data Index: 926976 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 4.2588. Min Range: -4.2588

Max Act: 3.9819. Min Act: -0.1700

Data Index: 1071694 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 4.2588. Min Range: -4.2588

Max Act: 3.9782. Min Act: -0.1700

Data Index: 1273626 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 4.2588. Min Range: -4.2588

Max Act: 3.9810. Min Act: -0.1700

Data Index: 72939 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 4.2588. Min Range: -4.2588

Max Act: 3.9557. Min Act: -0.1700

Data Index: 880605 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 4.2588. Min Range: -4.2588

Max Act: 3.9498. Min Act: -0.1700

Data Index: 325941 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 4.2588. Min Range: -4.2588

Max Act: 3.9356. Min Act: -0.1700

Data Index: 605135 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 4.2588. Min Range: -4.2588

Max Act: 3.9347. Min Act: -0.1700

Data Index: 1222444 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 4.2588. Min Range: -4.2588

Max Act: 3.8982. Min Act: -0.1700

Data Index: 147592 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 4.2588. Min Range: -4.2588

Max Act: 3.9151. Min Act: -0.1700

Data Index: 3462 (C4 (Web Text))

Max Activating Token Index: 184