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

Dataset: Open Web Text

Neuron 17 in Layer 1

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: 3.8370. Min Range: -3.8370

Max Act: 3.8370. Min Act: -0.1700

Data Index: 4732666 (Open Web Text)

Max Activating Token Index: 415

Text #1

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.8022. Min Act: -0.1700

Data Index: 2362343 (Open Web Text)

Max Activating Token Index: 243

Text #2

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7461. Min Act: -0.1700

Data Index: 8159529 (Open Web Text)

Max Activating Token Index: 474

Text #3

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7526. Min Act: -0.1700

Data Index: 1064122 (Open Web Text)

Max Activating Token Index: 321

Text #4

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7405. Min Act: -0.1700

Data Index: 582123 (Open Web Text)

Max Activating Token Index: 361

Text #5

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7285. Min Act: -0.1700

Data Index: 5413741 (Open Web Text)

Max Activating Token Index: 678

Text #6

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7644. Min Act: -0.1700

Data Index: 5151261 (Open Web Text)

Max Activating Token Index: 137

Text #7

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7422. Min Act: -0.1700

Data Index: 8521371 (Open Web Text)

Max Activating Token Index: 372

Text #8

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7516. Min Act: -0.1700

Data Index: 7836463 (Open Web Text)

Max Activating Token Index: 153

Text #9

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7331. Min Act: -0.1700

Data Index: 3262852 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6947. Min Act: -0.1700

Data Index: 2205662 (Open Web Text)

Max Activating Token Index: 125

Text #11

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7195. Min Act: -0.1700

Data Index: 3185278 (Open Web Text)

Max Activating Token Index: 695

Text #12

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7126. Min Act: -0.1700

Data Index: 3069325 (Open Web Text)

Max Activating Token Index: 279

Text #13

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6986. Min Act: -0.1700

Data Index: 7156215 (Open Web Text)

Max Activating Token Index: 947

Text #14

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7137. Min Act: -0.1700

Data Index: 87006 (Open Web Text)

Max Activating Token Index: 386

Text #15

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7055. Min Act: -0.1700

Data Index: 4012873 (Open Web Text)

Max Activating Token Index: 920

Text #16

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7042. Min Act: -0.1700

Data Index: 3455156 (Open Web Text)

Max Activating Token Index: 430

Text #17

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6714. Min Act: -0.1700

Data Index: 6594344 (Open Web Text)

Max Activating Token Index: 871

Text #18

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6854. Min Act: -0.1700

Data Index: 7585369 (Open Web Text)

Max Activating Token Index: 188

Text #19

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6756. Min Act: -0.1700

Data Index: 7759468 (Open Web Text)

Max Activating Token Index: 315