Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 570 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.1024. Min Act: -0.1700

Data Index: 58743 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.9444. Min Act: -0.1700

Data Index: 343632 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.9127. Min Act: -0.1700

Data Index: 141114 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8810. Min Act: -0.1700

Data Index: 580946 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8651. Min Act: -0.1700

Data Index: 1027150 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8651. Min Act: -0.1700

Data Index: 548561 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8651. Min Act: -0.1700

Data Index: 814272 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8492. Min Act: -0.1700

Data Index: 392367 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8492. Min Act: -0.1700

Data Index: 1145934 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8174. Min Act: -0.1700

Data Index: 1127562 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8174. Min Act: -0.1700

Data Index: 175593 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8174. Min Act: -0.1700

Data Index: 1058662 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8015. Min Act: -0.1700

Data Index: 1110961 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8174. Min Act: -0.1700

Data Index: 81720 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8333. Min Act: -0.1700

Data Index: 259703 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8174. Min Act: -0.1700

Data Index: 944916 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8015. Min Act: -0.1700

Data Index: 1136957 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.8015. Min Act: -0.1700

Data Index: 1040429 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.7855. Min Act: -0.1700

Data Index: 10836 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.1024. Min Range: -3.1024

Max Act: 2.7696. Min Act: -0.1700

Data Index: 369050 (C4 (Web Text))

Max Activating Token Index: 538