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

Dataset: Open Web Text

Neuron 1349 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: 3.0040. Min Range: -3.0040

Max Act: 3.0040. Min Act: -0.1700

Data Index: 6633164 (Open Web Text)

Max Activating Token Index: 221

Text #1

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.9588. Min Act: -0.1700

Data Index: 1350767 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8563. Min Act: -0.1700

Data Index: 3541829 (Open Web Text)

Max Activating Token Index: 804

Text #3

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8871. Min Act: -0.1700

Data Index: 5048427 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8887. Min Act: -0.1700

Data Index: 2158412 (Open Web Text)

Max Activating Token Index: 984

Text #5

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8732. Min Act: -0.1700

Data Index: 8662410 (Open Web Text)

Max Activating Token Index: 673

Text #6

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8344. Min Act: -0.1700

Data Index: 7776121 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8216. Min Act: -0.1700

Data Index: 8485474 (Open Web Text)

Max Activating Token Index: 188

Text #8

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8200. Min Act: -0.1700

Data Index: 5328715 (Open Web Text)

Max Activating Token Index: 630

Text #9

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8406. Min Act: -0.1700

Data Index: 5512315 (Open Web Text)

Max Activating Token Index: 909

Text #10

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8504. Min Act: -0.1700

Data Index: 979479 (Open Web Text)

Max Activating Token Index: 798

Text #11

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8333. Min Act: -0.1700

Data Index: 434731 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8188. Min Act: -0.1700

Data Index: 7075853 (Open Web Text)

Max Activating Token Index: 682

Text #13

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8080. Min Act: -0.1700

Data Index: 3218593 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8129. Min Act: -0.1700

Data Index: 7681120 (Open Web Text)

Max Activating Token Index: 571

Text #15

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.7824. Min Act: -0.1700

Data Index: 7266838 (Open Web Text)

Max Activating Token Index: 235

Text #16

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8253. Min Act: -0.1700

Data Index: 2256359 (Open Web Text)

Max Activating Token Index: 403

Text #17

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.8125. Min Act: -0.1700

Data Index: 2221712 (Open Web Text)

Max Activating Token Index: 613

Text #18

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.7633. Min Act: -0.1700

Data Index: 6751023 (Open Web Text)

Max Activating Token Index: 1011

Text #19

Max Range: 3.0040. Min Range: -3.0040

Max Act: 2.7765. Min Act: -0.1700

Data Index: 2298266 (Open Web Text)

Max Activating Token Index: 647