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

Dataset: Open Web Text

Neuron 296 in Layer 2

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: 4.0168. Min Range: -4.0168

Max Act: 4.0168. Min Act: -0.1700

Data Index: 6947994 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.9292. Min Act: -0.1700

Data Index: 170590 (Open Web Text)

Max Activating Token Index: 21

Text #2

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.8804. Min Act: -0.1700

Data Index: 3647899 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.7346. Min Act: -0.1700

Data Index: 3577663 (Open Web Text)

Max Activating Token Index: 666

Text #4

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.7572. Min Act: -0.1700

Data Index: 5603712 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.7930. Min Act: -0.1700

Data Index: 2525139 (Open Web Text)

Max Activating Token Index: 240

Text #6

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.7180. Min Act: -0.1700

Data Index: 8133317 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.7229. Min Act: -0.1700

Data Index: 415382 (Open Web Text)

Max Activating Token Index: 296

Text #8

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.7209. Min Act: -0.1700

Data Index: 6058621 (Open Web Text)

Max Activating Token Index: 643

Text #9

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.7008. Min Act: -0.1700

Data Index: 7629618 (Open Web Text)

Max Activating Token Index: 520

Text #10

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.6989. Min Act: -0.1700

Data Index: 5817462 (Open Web Text)

Max Activating Token Index: 904

Text #11

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.6677. Min Act: -0.1700

Data Index: 5378466 (Open Web Text)

Max Activating Token Index: 450

Text #12

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.6681. Min Act: -0.1700

Data Index: 612943 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.6517. Min Act: -0.1700

Data Index: 895369 (Open Web Text)

Max Activating Token Index: 318

Text #14

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.6837. Min Act: -0.1700

Data Index: 3450360 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.6598. Min Act: -0.1700

Data Index: 1934658 (Open Web Text)

Max Activating Token Index: 438

Text #16

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.6688. Min Act: -0.1700

Data Index: 4010882 (Open Web Text)

Max Activating Token Index: 924

Text #17

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.6777. Min Act: -0.1700

Data Index: 301658 (Open Web Text)

Max Activating Token Index: 522

Text #18

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.6381. Min Act: -0.1700

Data Index: 2529496 (Open Web Text)

Max Activating Token Index: 307

Text #19

Max Range: 4.0168. Min Range: -4.0168

Max Act: 3.6530. Min Act: -0.1700

Data Index: 3438653 (Open Web Text)

Max Activating Token Index: 247