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

Dataset: Open Web Text

Neuron 1365 in Layer 4

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: 6.4498. Min Range: -6.4498

Max Act: 6.4498. Min Act: -0.1700

Data Index: 103198 (Open Web Text)

Max Activating Token Index: 585

Text #1

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.2869. Min Act: -0.1700

Data Index: 2749382 (Open Web Text)

Max Activating Token Index: 504

Text #2

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.3100. Min Act: -0.1700

Data Index: 7882361 (Open Web Text)

Max Activating Token Index: 734

Text #3

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.2937. Min Act: -0.1700

Data Index: 1021125 (Open Web Text)

Max Activating Token Index: 108

Text #4

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.1564. Min Act: -0.1700

Data Index: 7842393 (Open Web Text)

Max Activating Token Index: 897

Text #5

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.2592. Min Act: -0.1700

Data Index: 3424603 (Open Web Text)

Max Activating Token Index: 509

Text #6

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.1584. Min Act: -0.1700

Data Index: 681188 (Open Web Text)

Max Activating Token Index: 549

Text #7

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.1615. Min Act: -0.1700

Data Index: 2007724 (Open Web Text)

Max Activating Token Index: 138

Text #8

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.1356. Min Act: -0.1700

Data Index: 5211385 (Open Web Text)

Max Activating Token Index: 971

Text #9

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.0979. Min Act: -0.1700

Data Index: 8819104 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.0275. Min Act: -0.1700

Data Index: 5113096 (Open Web Text)

Max Activating Token Index: 352

Text #11

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.0185. Min Act: -0.1700

Data Index: 4450049 (Open Web Text)

Max Activating Token Index: 189

Text #12

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.0084. Min Act: -0.1700

Data Index: 699199 (Open Web Text)

Max Activating Token Index: 69

Text #13

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.0988. Min Act: -0.1700

Data Index: 249711 (Open Web Text)

Max Activating Token Index: 562

Text #14

Max Range: 6.4498. Min Range: -6.4498

Max Act: 5.9974. Min Act: -0.1700

Data Index: 1826803 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.0240. Min Act: -0.1700

Data Index: 1653823 (Open Web Text)

Max Activating Token Index: 331

Text #16

Max Range: 6.4498. Min Range: -6.4498

Max Act: 5.9505. Min Act: -0.1700

Data Index: 4467703 (Open Web Text)

Max Activating Token Index: 363

Text #17

Max Range: 6.4498. Min Range: -6.4498

Max Act: 5.9954. Min Act: -0.1700

Data Index: 1057348 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 6.4498. Min Range: -6.4498

Max Act: 5.9769. Min Act: -0.1700

Data Index: 2156152 (Open Web Text)

Max Activating Token Index: 743

Text #19

Max Range: 6.4498. Min Range: -6.4498

Max Act: 6.0074. Min Act: -0.1700

Data Index: 2784256 (Open Web Text)

Max Activating Token Index: 845