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

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

Neuron 675 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: 3.7969. Min Range: -3.7969

Max Act: 3.7969. Min Act: -0.1696

Data Index: 1538978 (Python Code)

Max Activating Token Index: 543

Text #1

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.7146. Min Act: -0.1700

Data Index: 134356 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6621. Min Act: -0.1700

Data Index: 940306 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6561. Min Act: -0.1700

Data Index: 634911 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6737. Min Act: -0.1700

Data Index: 982656 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6558. Min Act: -0.1700

Data Index: 280968 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6365. Min Act: -0.1700

Data Index: 186692 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6385. Min Act: -0.1700

Data Index: 1455157 (Python Code)

Max Activating Token Index: 875

Text #8

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6245. Min Act: -0.1699

Data Index: 1402195 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6391. Min Act: -0.1700

Data Index: 135933 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6325. Min Act: -0.1700

Data Index: 43463 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6099. Min Act: -0.1700

Data Index: 77797 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6249. Min Act: -0.1700

Data Index: 1060021 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6145. Min Act: -0.1700

Data Index: 865801 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6086. Min Act: -0.1700

Data Index: 161093 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5847. Min Act: -0.1699

Data Index: 1573149 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5934. Min Act: -0.1699

Data Index: 1529154 (Python Code)

Max Activating Token Index: 365

Text #17

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5864. Min Act: -0.1700

Data Index: 397390 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5837. Min Act: -0.1700

Data Index: 1199776 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5923. Min Act: -0.1700

Data Index: 1337969 (C4 (Web Text))

Max Activating Token Index: 914