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

Dataset: Open Web Text

Neuron 1199 in Layer 0

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: 6.9444. Min Range: -6.9444

Max Act: 6.9444. Min Act: -0.1700

Data Index: 4378797 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.8359. Min Act: -0.1700

Data Index: 8221948 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.8666. Min Act: -0.1700

Data Index: 390022 (Open Web Text)

Max Activating Token Index: 802

Text #3

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.7704. Min Act: -0.1700

Data Index: 8461040 (Open Web Text)

Max Activating Token Index: 691

Text #4

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.8299. Min Act: -0.1700

Data Index: 4291669 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.8151. Min Act: -0.1700

Data Index: 7775639 (Open Web Text)

Max Activating Token Index: 342

Text #6

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.7854. Min Act: -0.1700

Data Index: 1564922 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.7360. Min Act: -0.1700

Data Index: 3913075 (Open Web Text)

Max Activating Token Index: 678

Text #8

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.7114. Min Act: -0.1700

Data Index: 7447006 (Open Web Text)

Max Activating Token Index: 691

Text #9

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.7324. Min Act: -0.1700

Data Index: 2866074 (Open Web Text)

Max Activating Token Index: 37

Text #10

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.7554. Min Act: -0.1700

Data Index: 5442158 (Open Web Text)

Max Activating Token Index: 468

Text #11

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.7666. Min Act: -0.1700

Data Index: 5239625 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.7374. Min Act: -0.1700

Data Index: 4291670 (Open Web Text)

Max Activating Token Index: 877

Text #13

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.6854. Min Act: -0.1700

Data Index: 5442159 (Open Web Text)

Max Activating Token Index: 189

Text #14

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.6874. Min Act: -0.1700

Data Index: 5613135 (Open Web Text)

Max Activating Token Index: 161

Text #15

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.7043. Min Act: -0.1700

Data Index: 6509050 (Open Web Text)

Max Activating Token Index: 57

Text #16

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.6594. Min Act: -0.1700

Data Index: 111992 (Open Web Text)

Max Activating Token Index: 940

Text #17

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.6716. Min Act: -0.1700

Data Index: 1125053 (Open Web Text)

Max Activating Token Index: 678

Text #18

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.6549. Min Act: -0.1700

Data Index: 5437297 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 6.9444. Min Range: -6.9444

Max Act: 6.6727. Min Act: -0.1700

Data Index: 407577 (Open Web Text)

Max Activating Token Index: 472