Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 803 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.5189. Min Act: -0.1700

Data Index: 451394 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.5189. Min Act: -0.1700

Data Index: 492469 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3939. Min Act: -0.1700

Data Index: 1086405 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.4876. Min Act: -0.1699

Data Index: 15385 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.4564. Min Act: -0.1700

Data Index: 950890 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.4564. Min Act: -0.1700

Data Index: 227336 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3939. Min Act: -0.1700

Data Index: 93251 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.4564. Min Act: -0.1700

Data Index: 293863 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.4251. Min Act: -0.1700

Data Index: 580030 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3314. Min Act: -0.1700

Data Index: 385072 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3626. Min Act: -0.1700

Data Index: 531687 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.2689. Min Act: -0.1699

Data Index: 294665 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3626. Min Act: -0.1700

Data Index: 781611 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3001. Min Act: -0.1700

Data Index: 185170 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3939. Min Act: -0.1700

Data Index: 322234 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3001. Min Act: -0.1700

Data Index: 468206 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3939. Min Act: -0.1700

Data Index: 114046 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3314. Min Act: -0.1699

Data Index: 381236 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.3939. Min Act: -0.1700

Data Index: 881120 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 7.5189. Min Range: -7.5189

Max Act: 7.2689. Min Act: -0.1700

Data Index: 864859 (C4 (Web Text))

Max Activating Token Index: 327