Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 668 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.4237. Min Act: -0.1700

Data Index: 1137911 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.3139. Min Act: -0.1700

Data Index: 352584 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2982. Min Act: -0.1700

Data Index: 1023346 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2510. Min Act: -0.1700

Data Index: 876463 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2510. Min Act: -0.1700

Data Index: 348196 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2510. Min Act: -0.1700

Data Index: 430001 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2196. Min Act: -0.1700

Data Index: 810636 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2353. Min Act: -0.1700

Data Index: 54261 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2196. Min Act: -0.1700

Data Index: 116854 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2196. Min Act: -0.1700

Data Index: 556043 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2196. Min Act: -0.1700

Data Index: 1183219 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2039. Min Act: -0.1700

Data Index: 95984 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2039. Min Act: -0.1700

Data Index: 692361 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.1881. Min Act: -0.1700

Data Index: 328156 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.1881. Min Act: -0.1700

Data Index: 371836 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2039. Min Act: -0.1700

Data Index: 995872 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.1881. Min Act: -0.1700

Data Index: 595466 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.2039. Min Act: -0.1700

Data Index: 626685 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.1724. Min Act: -0.1700

Data Index: 637907 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 3.4237. Min Range: -3.4237

Max Act: 3.1881. Min Act: -0.1700

Data Index: 375688 (C4 (Web Text))

Max Activating Token Index: 1016