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

Dataset: Open Web Text

Neuron 1125 in Layer 2

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: 1.7174. Min Range: -1.7174

Max Act: 1.7174. Min Act: -0.1700

Data Index: 6803472 (Open Web Text)

Max Activating Token Index: 665

Text #1

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.7006. Min Act: -0.1700

Data Index: 5124540 (Open Web Text)

Max Activating Token Index: 95

Text #2

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6901. Min Act: -0.1700

Data Index: 7151799 (Open Web Text)

Max Activating Token Index: 687

Text #3

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.7000. Min Act: -0.1700

Data Index: 6064475 (Open Web Text)

Max Activating Token Index: 319

Text #4

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6829. Min Act: -0.1700

Data Index: 2069097 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6828. Min Act: -0.1700

Data Index: 3030597 (Open Web Text)

Max Activating Token Index: 143

Text #6

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6683. Min Act: -0.1700

Data Index: 3361327 (Open Web Text)

Max Activating Token Index: 588

Text #7

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6495. Min Act: -0.1700

Data Index: 4930152 (Open Web Text)

Max Activating Token Index: 990

Text #8

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6703. Min Act: -0.1700

Data Index: 2426825 (Open Web Text)

Max Activating Token Index: 209

Text #9

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6757. Min Act: -0.1700

Data Index: 5027039 (Open Web Text)

Max Activating Token Index: 985

Text #10

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6406. Min Act: -0.1700

Data Index: 2961948 (Open Web Text)

Max Activating Token Index: 436

Text #11

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6412. Min Act: -0.1700

Data Index: 959470 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6432. Min Act: -0.1700

Data Index: 6019573 (Open Web Text)

Max Activating Token Index: 918

Text #13

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6475. Min Act: -0.1700

Data Index: 6777570 (Open Web Text)

Max Activating Token Index: 494

Text #14

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6294. Min Act: -0.1700

Data Index: 6088740 (Open Web Text)

Max Activating Token Index: 112

Text #15

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6295. Min Act: -0.1700

Data Index: 5040018 (Open Web Text)

Max Activating Token Index: 82

Text #16

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6312. Min Act: -0.1700

Data Index: 8704705 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6237. Min Act: -0.1700

Data Index: 1840874 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6122. Min Act: -0.1700

Data Index: 3645575 (Open Web Text)

Max Activating Token Index: 441

Text #19

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6130. Min Act: -0.1700

Data Index: 1969145 (Open Web Text)

Max Activating Token Index: 578