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

Dataset: Open Web Text

Neuron 40 in Layer 6

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: 3.3804. Min Range: -3.3804

Max Act: 3.3804. Min Act: -0.1700

Data Index: 4110653 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 3.3804. Min Range: -3.3804

Max Act: 3.1026. Min Act: -0.1700

Data Index: 5304857 (Open Web Text)

Max Activating Token Index: 391

Text #2

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.9759. Min Act: -0.1700

Data Index: 8618915 (Open Web Text)

Max Activating Token Index: 126

Text #3

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.9969. Min Act: -0.1700

Data Index: 1973620 (Open Web Text)

Max Activating Token Index: 582

Text #4

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.9701. Min Act: -0.1700

Data Index: 8166825 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.9662. Min Act: -0.1700

Data Index: 4324817 (Open Web Text)

Max Activating Token Index: 114

Text #6

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.9317. Min Act: -0.1700

Data Index: 1764170 (Open Web Text)

Max Activating Token Index: 624

Text #7

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8838. Min Act: -0.1700

Data Index: 8326436 (Open Web Text)

Max Activating Token Index: 685

Text #8

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8957. Min Act: -0.1700

Data Index: 6749604 (Open Web Text)

Max Activating Token Index: 715

Text #9

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8491. Min Act: -0.1700

Data Index: 5202262 (Open Web Text)

Max Activating Token Index: 1015

Text #10

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8186. Min Act: -0.1700

Data Index: 4365527 (Open Web Text)

Max Activating Token Index: 781

Text #11

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8448. Min Act: -0.1700

Data Index: 459270 (Open Web Text)

Max Activating Token Index: 689

Text #12

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8853. Min Act: -0.1700

Data Index: 5965557 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8358. Min Act: -0.1700

Data Index: 7287202 (Open Web Text)

Max Activating Token Index: 326

Text #14

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8524. Min Act: -0.1700

Data Index: 6679805 (Open Web Text)

Max Activating Token Index: 784

Text #15

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8238. Min Act: -0.1700

Data Index: 100718 (Open Web Text)

Max Activating Token Index: 723

Text #16

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8311. Min Act: -0.1700

Data Index: 5779066 (Open Web Text)

Max Activating Token Index: 595

Text #17

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8002. Min Act: -0.1700

Data Index: 3660931 (Open Web Text)

Max Activating Token Index: 776

Text #18

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8194. Min Act: -0.1700

Data Index: 3489401 (Open Web Text)

Max Activating Token Index: 453

Text #19

Max Range: 3.3804. Min Range: -3.3804

Max Act: 2.8086. Min Act: -0.1700

Data Index: 6902545 (Open Web Text)

Max Activating Token Index: 841