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

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

Neuron 651 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: 3.4858. Min Range: -3.4858

Max Act: 3.4858. Min Act: -0.1700

Data Index: 915347 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3760. Min Act: -0.1700

Data Index: 223987 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3917. Min Act: -0.1700

Data Index: 97384 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3446. Min Act: -0.1700

Data Index: 729827 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3446. Min Act: -0.1700

Data Index: 254887 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3446. Min Act: -0.1700

Data Index: 303827 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3290. Min Act: -0.1700

Data Index: 1119471 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3290. Min Act: -0.1700

Data Index: 884798 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3290. Min Act: -0.1700

Data Index: 848639 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3133. Min Act: -0.1700

Data Index: 109635 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.2975. Min Act: -0.1700

Data Index: 309505 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.2818. Min Act: -0.1700

Data Index: 988988 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.2818. Min Act: -0.1700

Data Index: 447113 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.2818. Min Act: -0.1700

Data Index: 591858 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.2347. Min Act: -0.1700

Data Index: 557487 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.2975. Min Act: -0.1700

Data Index: 895076 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.2661. Min Act: -0.1700

Data Index: 1042828 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.2190. Min Act: -0.1700

Data Index: 1026848 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.2504. Min Act: -0.1700

Data Index: 1093765 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.2661. Min Act: -0.1700

Data Index: 343204 (C4 (Web Text))

Max Activating Token Index: 163