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

Dataset: Open Web Text

Neuron 2942 in Layer 3

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: 4.9110. Min Range: -4.9110

Max Act: 4.9110. Min Act: -0.1700

Data Index: 6531167 (Open Web Text)

Max Activating Token Index: 856

Text #1

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.4249. Min Act: -0.1700

Data Index: 6571117 (Open Web Text)

Max Activating Token Index: 237

Text #2

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.3813. Min Act: -0.1700

Data Index: 6352524 (Open Web Text)

Max Activating Token Index: 501

Text #3

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.3265. Min Act: -0.1700

Data Index: 6774956 (Open Web Text)

Max Activating Token Index: 676

Text #4

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.3362. Min Act: -0.1700

Data Index: 4139781 (Open Web Text)

Max Activating Token Index: 408

Text #5

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.3354. Min Act: -0.1700

Data Index: 6737626 (Open Web Text)

Max Activating Token Index: 242

Text #6

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.3115. Min Act: -0.1700

Data Index: 467273 (Open Web Text)

Max Activating Token Index: 642

Text #7

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.2920. Min Act: -0.1700

Data Index: 1952915 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.2960. Min Act: -0.1700

Data Index: 6531172 (Open Web Text)

Max Activating Token Index: 177

Text #9

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.2685. Min Act: -0.1700

Data Index: 6571116 (Open Web Text)

Max Activating Token Index: 385

Text #10

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.3192. Min Act: -0.1700

Data Index: 7606703 (Open Web Text)

Max Activating Token Index: 107

Text #11

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.2961. Min Act: -0.1700

Data Index: 450499 (Open Web Text)

Max Activating Token Index: 336

Text #12

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.2652. Min Act: -0.1700

Data Index: 1019614 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.2452. Min Act: -0.1700

Data Index: 1610116 (Open Web Text)

Max Activating Token Index: 82

Text #14

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.2353. Min Act: -0.1700

Data Index: 5879846 (Open Web Text)

Max Activating Token Index: 501

Text #15

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.2357. Min Act: -0.1700

Data Index: 7718637 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.2215. Min Act: -0.1700

Data Index: 1364998 (Open Web Text)

Max Activating Token Index: 63

Text #17

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.1687. Min Act: -0.1700

Data Index: 8223408 (Open Web Text)

Max Activating Token Index: 869

Text #18

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.1968. Min Act: -0.1700

Data Index: 4569347 (Open Web Text)

Max Activating Token Index: 876

Text #19

Max Range: 4.9110. Min Range: -4.9110

Max Act: 4.1574. Min Act: -0.1700

Data Index: 5751368 (Open Web Text)

Max Activating Token Index: 576