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

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

Neuron 1880 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: 3.3977. Min Range: -3.3977

Max Act: 3.3977. Min Act: -0.1700

Data Index: 127781 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.3977. Min Act: -0.1700

Data Index: 905721 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.3663. Min Act: -0.1700

Data Index: 574295 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.3349. Min Act: -0.1700

Data Index: 946490 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2721. Min Act: -0.1700

Data Index: 199067 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2564. Min Act: -0.1700

Data Index: 983820 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2249. Min Act: -0.1700

Data Index: 102883 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2407. Min Act: -0.1700

Data Index: 27433 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2249. Min Act: -0.1700

Data Index: 1230092 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2092. Min Act: -0.1700

Data Index: 425242 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2092. Min Act: -0.1700

Data Index: 1287258 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2092. Min Act: -0.1700

Data Index: 1325545 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2092. Min Act: -0.1700

Data Index: 1151397 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2092. Min Act: -0.1700

Data Index: 862377 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2092. Min Act: -0.1700

Data Index: 38969 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2092. Min Act: -0.1700

Data Index: 767781 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.1935. Min Act: -0.1700

Data Index: 812268 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.2092. Min Act: -0.1700

Data Index: 811139 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.1935. Min Act: -0.1700

Data Index: 1194342 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 3.3977. Min Range: -3.3977

Max Act: 3.1935. Min Act: -0.1700

Data Index: 1171586 (C4 (Web Text))

Max Activating Token Index: 439