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

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

Neuron 1602 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: 3.4462. Min Range: -3.4462

Max Act: 3.4462. Min Act: -0.1700

Data Index: 1359593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.4382. Min Act: -0.1700

Data Index: 310216 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.4279. Min Act: -0.1700

Data Index: 730830 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.3902. Min Act: -0.1700

Data Index: 980449 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.3181. Min Act: -0.1700

Data Index: 2944 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.3188. Min Act: -0.1700

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.2748. Min Act: -0.1700

Data Index: 372407 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.2629. Min Act: -0.1700

Data Index: 7794 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.2509. Min Act: -0.1700

Data Index: 1253897 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.2287. Min Act: -0.1700

Data Index: 112098 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.2252. Min Act: -0.1700

Data Index: 582759 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.2207. Min Act: -0.1700

Data Index: 1328248 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.2454. Min Act: -0.1700

Data Index: 725806 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.1927. Min Act: -0.1700

Data Index: 469211 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.2117. Min Act: -0.1700

Data Index: 1349165 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.2043. Min Act: -0.1700

Data Index: 547119 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.1990. Min Act: -0.1700

Data Index: 577386 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.1799. Min Act: -0.1700

Data Index: 515543 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.1772. Min Act: -0.1700

Data Index: 1345554 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.1539. Min Act: -0.1700

Data Index: 212277 (C4 (Web Text))

Max Activating Token Index: 1023