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

Dataset: Open Web Text

Neuron 2442 in Layer 5

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: 4.1081. Min Range: -4.1081

Max Act: 4.1081. Min Act: -0.1700

Data Index: 7183101 (Open Web Text)

Max Activating Token Index: 724

Text #1

Max Range: 4.1081. Min Range: -4.1081

Max Act: 4.0586. Min Act: -0.1700

Data Index: 8591951 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8994. Min Act: -0.1700

Data Index: 2907950 (Open Web Text)

Max Activating Token Index: 107

Text #3

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8481. Min Act: -0.1700

Data Index: 3623973 (Open Web Text)

Max Activating Token Index: 429

Text #4

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7896. Min Act: -0.1700

Data Index: 4222255 (Open Web Text)

Max Activating Token Index: 76

Text #5

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8269. Min Act: -0.1700

Data Index: 155022 (Open Web Text)

Max Activating Token Index: 679

Text #6

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7902. Min Act: -0.1700

Data Index: 5648668 (Open Web Text)

Max Activating Token Index: 476

Text #7

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7665. Min Act: -0.1700

Data Index: 243435 (Open Web Text)

Max Activating Token Index: 315

Text #8

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7959. Min Act: -0.1700

Data Index: 2272095 (Open Web Text)

Max Activating Token Index: 381

Text #9

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8301. Min Act: -0.1700

Data Index: 7658873 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7543. Min Act: -0.1700

Data Index: 2068963 (Open Web Text)

Max Activating Token Index: 583

Text #11

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7261. Min Act: -0.1700

Data Index: 443781 (Open Web Text)

Max Activating Token Index: 794

Text #12

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7541. Min Act: -0.1700

Data Index: 3848637 (Open Web Text)

Max Activating Token Index: 744

Text #13

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7828. Min Act: -0.1700

Data Index: 6959100 (Open Web Text)

Max Activating Token Index: 477

Text #14

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8067. Min Act: -0.1700

Data Index: 5176360 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7586. Min Act: -0.1700

Data Index: 1161949 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7091. Min Act: -0.1700

Data Index: 6375335 (Open Web Text)

Max Activating Token Index: 396

Text #17

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7668. Min Act: -0.1700

Data Index: 7623575 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.7122. Min Act: -0.1700

Data Index: 8182258 (Open Web Text)

Max Activating Token Index: 206

Text #19

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.6804. Min Act: -0.1700

Data Index: 8043968 (Open Web Text)

Max Activating Token Index: 119