Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 3071 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.4364. Min Act: -0.1700

Data Index: 2177616 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.4095. Min Act: -0.1700

Data Index: 1156542 (Open Web Text)

Max Activating Token Index: 103

Text #2

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.4101. Min Act: -0.1700

Data Index: 4420079 (Open Web Text)

Max Activating Token Index: 767

Text #3

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.4051. Min Act: -0.1700

Data Index: 1796342 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3848. Min Act: -0.1700

Data Index: 7076232 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3854. Min Act: -0.1700

Data Index: 1490496 (Open Web Text)

Max Activating Token Index: 687

Text #6

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3840. Min Act: -0.1700

Data Index: 300123 (Open Web Text)

Max Activating Token Index: 99

Text #7

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3896. Min Act: -0.1700

Data Index: 7666670 (Open Web Text)

Max Activating Token Index: 93

Text #8

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3814. Min Act: -0.1700

Data Index: 6348646 (Open Web Text)

Max Activating Token Index: 712

Text #9

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3774. Min Act: -0.1700

Data Index: 2544089 (Open Web Text)

Max Activating Token Index: 765

Text #10

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3769. Min Act: -0.1700

Data Index: 7332877 (Open Web Text)

Max Activating Token Index: 98

Text #11

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3759. Min Act: -0.1700

Data Index: 5561092 (Open Web Text)

Max Activating Token Index: 723

Text #12

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3775. Min Act: -0.1700

Data Index: 1799731 (Open Web Text)

Max Activating Token Index: 702

Text #13

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3762. Min Act: -0.1700

Data Index: 307981 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3735. Min Act: -0.1700

Data Index: 3967597 (Open Web Text)

Max Activating Token Index: 108

Text #15

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3695. Min Act: -0.1700

Data Index: 5884998 (Open Web Text)

Max Activating Token Index: 687

Text #16

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3714. Min Act: -0.1700

Data Index: 6234271 (Open Web Text)

Max Activating Token Index: 769

Text #17

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3675. Min Act: -0.1700

Data Index: 6234269 (Open Web Text)

Max Activating Token Index: 701

Text #18

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3730. Min Act: -0.1700

Data Index: 1388731 (Open Web Text)

Max Activating Token Index: 712

Text #19

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3766. Min Act: -0.1700

Data Index: 1823589 (Open Web Text)

Max Activating Token Index: 734