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

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

Neuron 98 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.7179. Min Act: -0.1700

Data Index: 1095892 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.6554. Min Act: -0.1700

Data Index: 998946 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.6867. Min Act: -0.1700

Data Index: 17442 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.5929. Min Act: -0.1700

Data Index: 1185039 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.4054. Min Act: -0.1700

Data Index: 1036709 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.3742. Min Act: -0.1700

Data Index: 1219304 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.3742. Min Act: -0.1700

Data Index: 705966 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.4367. Min Act: -0.1700

Data Index: 1065003 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.3742. Min Act: -0.1700

Data Index: 987725 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.3117. Min Act: -0.1700

Data Index: 467545 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.4054. Min Act: -0.1700

Data Index: 424098 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.3429. Min Act: -0.1700

Data Index: 607075 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.3117. Min Act: -0.1700

Data Index: 507781 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.2492. Min Act: -0.1700

Data Index: 1048858 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.2804. Min Act: -0.1700

Data Index: 744496 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.2492. Min Act: -0.1700

Data Index: 453085 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.2492. Min Act: -0.1700

Data Index: 611549 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.2492. Min Act: -0.1700

Data Index: 1240374 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.2804. Min Act: -0.1700

Data Index: 919206 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 5.7179. Min Range: -5.7179

Max Act: 5.2179. Min Act: -0.1700

Data Index: 132536 (C4 (Web Text))

Max Activating Token Index: 295