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

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

Neuron 558 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: 3.4941. Min Range: -3.4941

Max Act: 3.4941. Min Act: -0.1700

Data Index: 1196383 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.4168. Min Act: -0.1700

Data Index: 1134668 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.3940. Min Act: -0.1700

Data Index: 1121338 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.3151. Min Act: -0.1700

Data Index: 188396 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.3201. Min Act: -0.1700

Data Index: 1183694 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.3094. Min Act: -0.1700

Data Index: 200814 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2882. Min Act: -0.1700

Data Index: 296876 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2777. Min Act: -0.1700

Data Index: 988135 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2701. Min Act: -0.1700

Data Index: 1014130 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2775. Min Act: -0.1700

Data Index: 561665 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2541. Min Act: -0.1700

Data Index: 435785 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2456. Min Act: -0.1700

Data Index: 208761 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2359. Min Act: -0.1700

Data Index: 26181 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2243. Min Act: -0.1700

Data Index: 886658 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2262. Min Act: -0.1700

Data Index: 1248242 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2111. Min Act: -0.1700

Data Index: 431204 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2047. Min Act: -0.1700

Data Index: 1002804 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2112. Min Act: -0.1700

Data Index: 946583 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.2028. Min Act: -0.1700

Data Index: 153137 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 3.4941. Min Range: -3.4941

Max Act: 3.1996. Min Act: -0.1699

Data Index: 185861 (C4 (Web Text))

Max Activating Token Index: 153