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

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

Neuron 1696 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: 3.6914. Min Range: -3.6914

Max Act: 3.6914. Min Act: -0.1700

Data Index: 1330357 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6130. Min Act: -0.1699

Data Index: 137782 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6185. Min Act: -0.1699

Data Index: 1162874 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5985. Min Act: -0.1700

Data Index: 4974 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5671. Min Act: -0.1700

Data Index: 640720 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5186. Min Act: -0.1700

Data Index: 341184 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5106. Min Act: -0.1700

Data Index: 397873 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5192. Min Act: -0.1700

Data Index: 44541 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5098. Min Act: -0.1700

Data Index: 109704 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5097. Min Act: -0.1697

Data Index: 693002 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4979. Min Act: -0.1700

Data Index: 101676 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4803. Min Act: -0.1700

Data Index: 745945 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4904. Min Act: -0.1700

Data Index: 374063 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4725. Min Act: -0.1700

Data Index: 1156861 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4618. Min Act: -0.1700

Data Index: 1175848 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4650. Min Act: -0.1700

Data Index: 1286047 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4656. Min Act: -0.1700

Data Index: 1197094 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4587. Min Act: -0.1700

Data Index: 194213 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4519. Min Act: -0.1700

Data Index: 166845 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4552. Min Act: -0.1700

Data Index: 835249 (C4 (Web Text))

Max Activating Token Index: 547