Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 967 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.5971. Min Act: -0.1700

Data Index: 590860 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.5188. Min Act: -0.1700

Data Index: 441750 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.4091. Min Act: -0.1700

Data Index: 1301701 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.3934. Min Act: -0.1700

Data Index: 154010 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.3463. Min Act: -0.1700

Data Index: 984937 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.3149. Min Act: -0.1700

Data Index: 685949 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2678. Min Act: -0.1700

Data Index: 809464 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2521. Min Act: -0.1700

Data Index: 1040733 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2678. Min Act: -0.1700

Data Index: 949498 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2521. Min Act: -0.1700

Data Index: 478424 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2678. Min Act: -0.1700

Data Index: 34672 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2678. Min Act: -0.1700

Data Index: 414075 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2678. Min Act: -0.1700

Data Index: 169957 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2521. Min Act: -0.1700

Data Index: 163133 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2049. Min Act: -0.1700

Data Index: 957192 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2206. Min Act: -0.1700

Data Index: 891571 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.1892. Min Act: -0.1700

Data Index: 145864 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.2049. Min Act: -0.1700

Data Index: 344861 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.1892. Min Act: -0.1700

Data Index: 782069 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.1892. Min Act: -0.1700

Data Index: 607432 (C4 (Web Text))

Max Activating Token Index: 565