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

Dataset: Open Web Text

Neuron 2479 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: 3.4459. Min Range: -3.4459

Max Act: 3.4459. Min Act: -0.1700

Data Index: 3162520 (Open Web Text)

Max Activating Token Index: 41

Text #1

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.4304. Min Act: -0.1700

Data Index: 4670393 (Open Web Text)

Max Activating Token Index: 103

Text #2

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.4203. Min Act: -0.1700

Data Index: 4977437 (Open Web Text)

Max Activating Token Index: 31

Text #3

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.4128. Min Act: -0.1700

Data Index: 1418079 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.4026. Min Act: -0.1700

Data Index: 8514901 (Open Web Text)

Max Activating Token Index: 22

Text #5

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3872. Min Act: -0.1700

Data Index: 1661714 (Open Web Text)

Max Activating Token Index: 52

Text #6

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3813. Min Act: -0.1700

Data Index: 489705 (Open Web Text)

Max Activating Token Index: 161

Text #7

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.4070. Min Act: -0.1700

Data Index: 6341245 (Open Web Text)

Max Activating Token Index: 192

Text #8

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3915. Min Act: -0.1700

Data Index: 153461 (Open Web Text)

Max Activating Token Index: 517

Text #9

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3801. Min Act: -0.1700

Data Index: 8188035 (Open Web Text)

Max Activating Token Index: 665

Text #10

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3551. Min Act: -0.1700

Data Index: 8020033 (Open Web Text)

Max Activating Token Index: 414

Text #11

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3848. Min Act: -0.1700

Data Index: 3646930 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3651. Min Act: -0.1700

Data Index: 3592703 (Open Web Text)

Max Activating Token Index: 641

Text #13

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3829. Min Act: -0.1700

Data Index: 7765992 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3785. Min Act: -0.1700

Data Index: 6410908 (Open Web Text)

Max Activating Token Index: 695

Text #15

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3655. Min Act: -0.1700

Data Index: 704251 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3781. Min Act: -0.1700

Data Index: 3477927 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3742. Min Act: -0.1700

Data Index: 3179330 (Open Web Text)

Max Activating Token Index: 793

Text #18

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3554. Min Act: -0.1700

Data Index: 4919534 (Open Web Text)

Max Activating Token Index: 479

Text #19

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3669. Min Act: -0.1700

Data Index: 1229964 (Open Web Text)

Max Activating Token Index: 452