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

Dataset: Open Web Text

Neuron 1643 in Layer 5

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: 3.4894. Min Range: -3.4894

Max Act: 3.4894. Min Act: -0.1700

Data Index: 361742 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.4729. Min Act: -0.1700

Data Index: 7853429 (Open Web Text)

Max Activating Token Index: 282

Text #2

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.4855. Min Act: -0.1700

Data Index: 3410306 (Open Web Text)

Max Activating Token Index: 488

Text #3

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3787. Min Act: -0.1700

Data Index: 2081303 (Open Web Text)

Max Activating Token Index: 716

Text #4

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3621. Min Act: -0.1700

Data Index: 5582114 (Open Web Text)

Max Activating Token Index: 73

Text #5

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3291. Min Act: -0.1700

Data Index: 2011122 (Open Web Text)

Max Activating Token Index: 786

Text #6

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3412. Min Act: -0.1700

Data Index: 5796730 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3123. Min Act: -0.1700

Data Index: 218811 (Open Web Text)

Max Activating Token Index: 741

Text #8

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3077. Min Act: -0.1700

Data Index: 2777601 (Open Web Text)

Max Activating Token Index: 874

Text #9

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2896. Min Act: -0.1700

Data Index: 4233791 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2738. Min Act: -0.1700

Data Index: 2111327 (Open Web Text)

Max Activating Token Index: 729

Text #11

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2712. Min Act: -0.1700

Data Index: 6345087 (Open Web Text)

Max Activating Token Index: 685

Text #12

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2726. Min Act: -0.1700

Data Index: 5912751 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2613. Min Act: -0.1700

Data Index: 8204101 (Open Web Text)

Max Activating Token Index: 103

Text #14

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2375. Min Act: -0.1700

Data Index: 5325444 (Open Web Text)

Max Activating Token Index: 861

Text #15

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2297. Min Act: -0.1700

Data Index: 1624923 (Open Web Text)

Max Activating Token Index: 407

Text #16

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2302. Min Act: -0.1700

Data Index: 4778424 (Open Web Text)

Max Activating Token Index: 767

Text #17

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2262. Min Act: -0.1700

Data Index: 3703257 (Open Web Text)

Max Activating Token Index: 200

Text #18

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2135. Min Act: -0.1700

Data Index: 3827227 (Open Web Text)

Max Activating Token Index: 440

Text #19

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2246. Min Act: -0.1700

Data Index: 7007145 (Open Web Text)

Max Activating Token Index: 291