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

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

Neuron 302 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.3854. Min Act: -0.1699

Data Index: 739603 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.3697. Min Act: -0.1700

Data Index: 507614 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.3069. Min Act: -0.1700

Data Index: 1256543 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.4011. Min Act: -0.1700

Data Index: 862039 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.3854. Min Act: -0.1700

Data Index: 762023 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.3069. Min Act: -0.1700

Data Index: 613580 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.3069. Min Act: -0.1700

Data Index: 1189585 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.2912. Min Act: -0.1700

Data Index: 989605 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.2755. Min Act: -0.1700

Data Index: 1136334 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.2598. Min Act: -0.1700

Data Index: 594958 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.2126. Min Act: -0.1700

Data Index: 748323 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.2284. Min Act: -0.1700

Data Index: 796000 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.1654. Min Act: -0.1700

Data Index: 614646 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.1969. Min Act: -0.1700

Data Index: 1076822 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.1654. Min Act: -0.1700

Data Index: 1020787 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.1654. Min Act: -0.1700

Data Index: 831770 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.1812. Min Act: -0.1700

Data Index: 1282263 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.1497. Min Act: -0.1700

Data Index: 222754 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.1654. Min Act: -0.1700

Data Index: 1102249 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 3.4011. Min Range: -3.4011

Max Act: 3.1182. Min Act: -0.1700

Data Index: 872086 (C4 (Web Text))

Max Activating Token Index: 575