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

Dataset: Open Web Text

Neuron 1787 in Layer 3

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: 3.6023. Min Range: -3.6023

Max Act: 3.6023. Min Act: -0.1700

Data Index: 4813961 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.5032. Min Act: -0.1700

Data Index: 4385114 (Open Web Text)

Max Activating Token Index: 301

Text #2

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.5015. Min Act: -0.1700

Data Index: 2815656 (Open Web Text)

Max Activating Token Index: 451

Text #3

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4761. Min Act: -0.1700

Data Index: 3164556 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4606. Min Act: -0.1700

Data Index: 3781422 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4551. Min Act: -0.1700

Data Index: 5677720 (Open Web Text)

Max Activating Token Index: 55

Text #6

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4432. Min Act: -0.1700

Data Index: 2967285 (Open Web Text)

Max Activating Token Index: 687

Text #7

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4628. Min Act: -0.1700

Data Index: 5911518 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4296. Min Act: -0.1700

Data Index: 3232329 (Open Web Text)

Max Activating Token Index: 244

Text #9

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4284. Min Act: -0.1700

Data Index: 2598105 (Open Web Text)

Max Activating Token Index: 191

Text #10

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4170. Min Act: -0.1700

Data Index: 5198577 (Open Web Text)

Max Activating Token Index: 218

Text #11

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3895. Min Act: -0.1700

Data Index: 6397545 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4140. Min Act: -0.1700

Data Index: 6050723 (Open Web Text)

Max Activating Token Index: 633

Text #13

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3766. Min Act: -0.1700

Data Index: 1945432 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4295. Min Act: -0.1700

Data Index: 3778023 (Open Web Text)

Max Activating Token Index: 676

Text #15

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4174. Min Act: -0.1700

Data Index: 8294808 (Open Web Text)

Max Activating Token Index: 253

Text #16

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3960. Min Act: -0.1700

Data Index: 7281628 (Open Web Text)

Max Activating Token Index: 505

Text #17

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4154. Min Act: -0.1700

Data Index: 7720632 (Open Web Text)

Max Activating Token Index: 382

Text #18

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.4153. Min Act: -0.1700

Data Index: 1151544 (Open Web Text)

Max Activating Token Index: 493

Text #19

Max Range: 3.6023. Min Range: -3.6023

Max Act: 3.3897. Min Act: -0.1700

Data Index: 8228351 (Open Web Text)

Max Activating Token Index: 224