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

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

Neuron 75 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: 3.6881. Min Range: -3.6881

Max Act: 3.6881. Min Act: -0.1700

Data Index: 234542 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.6819. Min Act: -0.1700

Data Index: 806885 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.6277. Min Act: -0.1700

Data Index: 539175 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.6110. Min Act: -0.1700

Data Index: 979096 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.6029. Min Act: -0.1700

Data Index: 114793 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.6026. Min Act: -0.1700

Data Index: 905891 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.6257. Min Act: -0.1700

Data Index: 65392 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.5994. Min Act: -0.1700

Data Index: 350371 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.5695. Min Act: -0.1700

Data Index: 851369 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.5751. Min Act: -0.1700

Data Index: 436780 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.5429. Min Act: -0.1700

Data Index: 457941 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.5081. Min Act: -0.1700

Data Index: 212148 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.5443. Min Act: -0.1700

Data Index: 1001005 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.5110. Min Act: -0.1700

Data Index: 702745 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.4962. Min Act: -0.1700

Data Index: 619952 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.4940. Min Act: -0.1700

Data Index: 436825 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.4815. Min Act: -0.1700

Data Index: 979008 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.5066. Min Act: -0.1700

Data Index: 92769 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.5057. Min Act: -0.1700

Data Index: 1126296 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.4525. Min Act: -0.1700

Data Index: 324347 (C4 (Web Text))

Max Activating Token Index: 427