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

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

Neuron 631 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: 2.7101. Min Range: -2.7101

Max Act: 2.7101. Min Act: -0.1700

Data Index: 996846 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.6161. Min Act: -0.1700

Data Index: 1016313 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.6442. Min Act: -0.1700

Data Index: 102210 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.6177. Min Act: -0.1700

Data Index: 381377 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.6071. Min Act: -0.1700

Data Index: 477127 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5761. Min Act: -0.1700

Data Index: 1071037 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5818. Min Act: -0.1700

Data Index: 1143823 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5776. Min Act: -0.1700

Data Index: 1247610 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5818. Min Act: -0.1700

Data Index: 894434 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5965. Min Act: -0.1700

Data Index: 648573 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5643. Min Act: -0.1700

Data Index: 1330594 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5597. Min Act: -0.1700

Data Index: 1256507 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5696. Min Act: -0.1700

Data Index: 926791 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5636. Min Act: -0.1700

Data Index: 289075 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5699. Min Act: -0.1700

Data Index: 946730 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5727. Min Act: -0.1700

Data Index: 270221 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5602. Min Act: -0.1700

Data Index: 395407 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5403. Min Act: -0.1700

Data Index: 1563652 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5424. Min Act: -0.1700

Data Index: 1371940 (Python Code)

Max Activating Token Index: 361

Text #19

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5415. Min Act: -0.1700

Data Index: 664023 (C4 (Web Text))

Max Activating Token Index: 866