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

Dataset: Open Web Text

Neuron 2522 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: 3.3416. Min Range: -3.3416

Max Act: 3.3416. Min Act: -0.1700

Data Index: 7743199 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.3088. Min Act: -0.1700

Data Index: 4658952 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2706. Min Act: -0.1700

Data Index: 2727851 (Open Web Text)

Max Activating Token Index: 307

Text #3

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2904. Min Act: -0.1700

Data Index: 3618728 (Open Web Text)

Max Activating Token Index: 719

Text #4

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2733. Min Act: -0.1700

Data Index: 5138460 (Open Web Text)

Max Activating Token Index: 346

Text #5

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2849. Min Act: -0.1700

Data Index: 4288582 (Open Web Text)

Max Activating Token Index: 476

Text #6

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2841. Min Act: -0.1700

Data Index: 2029115 (Open Web Text)

Max Activating Token Index: 571

Text #7

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2666. Min Act: -0.1700

Data Index: 2775983 (Open Web Text)

Max Activating Token Index: 558

Text #8

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2583. Min Act: -0.1700

Data Index: 7150442 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2601. Min Act: -0.1700

Data Index: 3156085 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2293. Min Act: -0.1700

Data Index: 8193413 (Open Web Text)

Max Activating Token Index: 263

Text #11

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2044. Min Act: -0.1700

Data Index: 1735182 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2245. Min Act: -0.1700

Data Index: 1295623 (Open Web Text)

Max Activating Token Index: 498

Text #13

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2026. Min Act: -0.1700

Data Index: 2268835 (Open Web Text)

Max Activating Token Index: 402

Text #14

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2000. Min Act: -0.1700

Data Index: 4973220 (Open Web Text)

Max Activating Token Index: 282

Text #15

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.1707. Min Act: -0.1700

Data Index: 5059749 (Open Web Text)

Max Activating Token Index: 732

Text #16

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.2027. Min Act: -0.1700

Data Index: 6734609 (Open Web Text)

Max Activating Token Index: 927

Text #17

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.1933. Min Act: -0.1700

Data Index: 4810989 (Open Web Text)

Max Activating Token Index: 310

Text #18

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.1890. Min Act: -0.1700

Data Index: 3613908 (Open Web Text)

Max Activating Token Index: 81

Text #19

Max Range: 3.3416. Min Range: -3.3416

Max Act: 3.1776. Min Act: -0.1700

Data Index: 6700769 (Open Web Text)

Max Activating Token Index: 210