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

Dataset: Open Web Text

Neuron 237 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: 1.7984. Min Range: -1.7984

Max Act: 1.7984. Min Act: -0.1700

Data Index: 2914866 (Open Web Text)

Max Activating Token Index: 225

Text #1

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.7656. Min Act: -0.1700

Data Index: 4702567 (Open Web Text)

Max Activating Token Index: 812

Text #2

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.7364. Min Act: -0.1700

Data Index: 7745813 (Open Web Text)

Max Activating Token Index: 142

Text #3

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.7333. Min Act: -0.1700

Data Index: 5726285 (Open Web Text)

Max Activating Token Index: 590

Text #4

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.7225. Min Act: -0.1700

Data Index: 1523094 (Open Web Text)

Max Activating Token Index: 147

Text #5

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.7280. Min Act: -0.1700

Data Index: 2028589 (Open Web Text)

Max Activating Token Index: 802

Text #6

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6990. Min Act: -0.1696

Data Index: 8502834 (Open Web Text)

Max Activating Token Index: 335

Text #7

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.7012. Min Act: -0.1700

Data Index: 1837006 (Open Web Text)

Max Activating Token Index: 250

Text #8

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6861. Min Act: -0.1700

Data Index: 7945327 (Open Web Text)

Max Activating Token Index: 60

Text #9

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6929. Min Act: -0.1700

Data Index: 7891165 (Open Web Text)

Max Activating Token Index: 542

Text #10

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6729. Min Act: -0.1700

Data Index: 249047 (Open Web Text)

Max Activating Token Index: 1013

Text #11

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6716. Min Act: -0.1700

Data Index: 5674548 (Open Web Text)

Max Activating Token Index: 825

Text #12

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6761. Min Act: -0.1700

Data Index: 4714560 (Open Web Text)

Max Activating Token Index: 578

Text #13

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6729. Min Act: -0.1700

Data Index: 8524254 (Open Web Text)

Max Activating Token Index: 807

Text #14

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6688. Min Act: -0.1700

Data Index: 3094950 (Open Web Text)

Max Activating Token Index: 183

Text #15

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6718. Min Act: -0.1700

Data Index: 3591800 (Open Web Text)

Max Activating Token Index: 800

Text #16

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6630. Min Act: -0.1700

Data Index: 4709471 (Open Web Text)

Max Activating Token Index: 294

Text #17

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6671. Min Act: -0.1700

Data Index: 1824404 (Open Web Text)

Max Activating Token Index: 529

Text #18

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6567. Min Act: -0.1700

Data Index: 1950992 (Open Web Text)

Max Activating Token Index: 287

Text #19

Max Range: 1.7984. Min Range: -1.7984

Max Act: 1.6498. Min Act: -0.1700

Data Index: 324112 (Open Web Text)

Max Activating Token Index: 328