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

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

Neuron 1452 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: 3.6407. Min Range: -3.6407

Max Act: 3.6407. Min Act: -0.1700

Data Index: 1110677 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.6250. Min Act: -0.1700

Data Index: 197163 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.5937. Min Act: -0.1700

Data Index: 877365 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.5467. Min Act: -0.1700

Data Index: 795222 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.5311. Min Act: -0.1700

Data Index: 937345 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.5311. Min Act: -0.1700

Data Index: 601528 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.5311. Min Act: -0.1700

Data Index: 975375 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.5154. Min Act: -0.1700

Data Index: 242636 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4841. Min Act: -0.1700

Data Index: 220143 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4841. Min Act: -0.1700

Data Index: 168481 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4997. Min Act: -0.1700

Data Index: 634583 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4997. Min Act: -0.1700

Data Index: 986378 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.5154. Min Act: -0.1700

Data Index: 1044034 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4997. Min Act: -0.1700

Data Index: 1303858 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4841. Min Act: -0.1700

Data Index: 507119 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4997. Min Act: -0.1700

Data Index: 229794 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4684. Min Act: -0.1700

Data Index: 137518 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4684. Min Act: -0.1700

Data Index: 367488 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4841. Min Act: -0.1700

Data Index: 468222 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 3.6407. Min Range: -3.6407

Max Act: 3.4684. Min Act: -0.1700

Data Index: 1155690 (C4 (Web Text))

Max Activating Token Index: 497