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

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

Neuron 1635 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.6253. Min Act: -0.1700

Data Index: 1128220 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.6097. Min Act: -0.1700

Data Index: 979898 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5784. Min Act: -0.1700

Data Index: 1327847 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.6097. Min Act: -0.1700

Data Index: 294511 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5784. Min Act: -0.1700

Data Index: 1155242 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5470. Min Act: -0.1700

Data Index: 170087 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5784. Min Act: -0.1700

Data Index: 608914 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5940. Min Act: -0.1700

Data Index: 787919 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4844. Min Act: -0.1700

Data Index: 1298671 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5470. Min Act: -0.1700

Data Index: 380147 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5627. Min Act: -0.1700

Data Index: 372924 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5157. Min Act: -0.1700

Data Index: 903166 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5314. Min Act: -0.1700

Data Index: 564397 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5314. Min Act: -0.1700

Data Index: 733151 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5000. Min Act: -0.1700

Data Index: 414085 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5000. Min Act: -0.1700

Data Index: 279760 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5157. Min Act: -0.1700

Data Index: 557347 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5157. Min Act: -0.1700

Data Index: 594119 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4530. Min Act: -0.1700

Data Index: 19291 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5000. Min Act: -0.1700

Data Index: 679113 (C4 (Web Text))

Max Activating Token Index: 911