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

Dataset: Open Web Text

Neuron 2453 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: 1.6661. Min Range: -1.6661

Max Act: 1.6557. Min Act: -0.1700

Data Index: 7035282 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.6661. Min Act: -0.1700

Data Index: 574352 (Open Web Text)

Max Activating Token Index: 248

Text #2

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.6448. Min Act: -0.1700

Data Index: 6234783 (Open Web Text)

Max Activating Token Index: 125

Text #3

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.6236. Min Act: -0.1700

Data Index: 8640574 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.6275. Min Act: -0.1700

Data Index: 5121640 (Open Web Text)

Max Activating Token Index: 465

Text #5

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.6060. Min Act: -0.1700

Data Index: 5034181 (Open Web Text)

Max Activating Token Index: 86

Text #6

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.6133. Min Act: -0.1700

Data Index: 2106398 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.6015. Min Act: -0.1700

Data Index: 2599431 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5911. Min Act: -0.1700

Data Index: 1843986 (Open Web Text)

Max Activating Token Index: 796

Text #9

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5880. Min Act: -0.1700

Data Index: 1532544 (Open Web Text)

Max Activating Token Index: 116

Text #10

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5775. Min Act: -0.1700

Data Index: 6259174 (Open Web Text)

Max Activating Token Index: 297

Text #11

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5796. Min Act: -0.1700

Data Index: 8699051 (Open Web Text)

Max Activating Token Index: 133

Text #12

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5822. Min Act: -0.1700

Data Index: 6424989 (Open Web Text)

Max Activating Token Index: 643

Text #13

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5743. Min Act: -0.1700

Data Index: 7239937 (Open Web Text)

Max Activating Token Index: 332

Text #14

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5693. Min Act: -0.1700

Data Index: 2021353 (Open Web Text)

Max Activating Token Index: 184

Text #15

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5670. Min Act: -0.1700

Data Index: 5535521 (Open Web Text)

Max Activating Token Index: 530

Text #16

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5652. Min Act: -0.1700

Data Index: 7951881 (Open Web Text)

Max Activating Token Index: 443

Text #17

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5811. Min Act: -0.1700

Data Index: 4925420 (Open Web Text)

Max Activating Token Index: 731

Text #18

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5680. Min Act: -0.1700

Data Index: 2591022 (Open Web Text)

Max Activating Token Index: 753

Text #19

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.5579. Min Act: -0.1700

Data Index: 7266551 (Open Web Text)

Max Activating Token Index: 105