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

Dataset: Open Web Text

Neuron 142 in Layer 4

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: 3.9878. Min Range: -3.9878

Max Act: 3.9878. Min Act: -0.1700

Data Index: 830033 (Open Web Text)

Max Activating Token Index: 34

Text #1

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9498. Min Act: -0.1700

Data Index: 2881763 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9594. Min Act: -0.1700

Data Index: 7654969 (Open Web Text)

Max Activating Token Index: 81

Text #3

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9588. Min Act: -0.1700

Data Index: 7443589 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9802. Min Act: -0.1700

Data Index: 650279 (Open Web Text)

Max Activating Token Index: 28

Text #5

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9599. Min Act: -0.1700

Data Index: 3399855 (Open Web Text)

Max Activating Token Index: 349

Text #6

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9588. Min Act: -0.1700

Data Index: 6522152 (Open Web Text)

Max Activating Token Index: 280

Text #7

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9752. Min Act: -0.1700

Data Index: 465780 (Open Web Text)

Max Activating Token Index: 466

Text #8

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9353. Min Act: -0.1700

Data Index: 3603754 (Open Web Text)

Max Activating Token Index: 850

Text #9

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9166. Min Act: -0.1700

Data Index: 6697243 (Open Web Text)

Max Activating Token Index: 180

Text #10

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9175. Min Act: -0.1700

Data Index: 192698 (Open Web Text)

Max Activating Token Index: 94

Text #11

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9231. Min Act: -0.1700

Data Index: 650277 (Open Web Text)

Max Activating Token Index: 217

Text #12

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9328. Min Act: -0.1700

Data Index: 6106149 (Open Web Text)

Max Activating Token Index: 357

Text #13

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9151. Min Act: -0.1700

Data Index: 4776784 (Open Web Text)

Max Activating Token Index: 157

Text #14

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9496. Min Act: -0.1700

Data Index: 4159565 (Open Web Text)

Max Activating Token Index: 671

Text #15

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9480. Min Act: -0.1700

Data Index: 7791405 (Open Web Text)

Max Activating Token Index: 411

Text #16

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9238. Min Act: -0.1700

Data Index: 1537832 (Open Web Text)

Max Activating Token Index: 96

Text #17

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9305. Min Act: -0.1700

Data Index: 4314779 (Open Web Text)

Max Activating Token Index: 586

Text #18

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.9199. Min Act: -0.1700

Data Index: 8189822 (Open Web Text)

Max Activating Token Index: 225

Text #19

Max Range: 3.9878. Min Range: -3.9878

Max Act: 3.8961. Min Act: -0.1700

Data Index: 1939287 (Open Web Text)

Max Activating Token Index: 245