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

Dataset: Open Web Text

Neuron 264 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: 5.7053. Min Range: -5.7053

Max Act: 5.7053. Min Act: -0.1700

Data Index: 1189391 (Open Web Text)

Max Activating Token Index: 707

Text #1

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.6269. Min Act: -0.1700

Data Index: 7786868 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.4580. Min Act: -0.1700

Data Index: 7317405 (Open Web Text)

Max Activating Token Index: 920

Text #3

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.4602. Min Act: -0.1700

Data Index: 8466721 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.4416. Min Act: -0.1700

Data Index: 7034479 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3723. Min Act: -0.1700

Data Index: 951903 (Open Web Text)

Max Activating Token Index: 772

Text #6

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.4571. Min Act: -0.1700

Data Index: 5838529 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3938. Min Act: -0.1700

Data Index: 8397372 (Open Web Text)

Max Activating Token Index: 821

Text #8

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3779. Min Act: -0.1700

Data Index: 7328918 (Open Web Text)

Max Activating Token Index: 206

Text #9

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3608. Min Act: -0.1700

Data Index: 4019586 (Open Web Text)

Max Activating Token Index: 335

Text #10

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3862. Min Act: -0.1700

Data Index: 4376428 (Open Web Text)

Max Activating Token Index: 469

Text #11

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3665. Min Act: -0.1700

Data Index: 7317404 (Open Web Text)

Max Activating Token Index: 766

Text #12

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3190. Min Act: -0.1700

Data Index: 1136962 (Open Web Text)

Max Activating Token Index: 152

Text #13

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3342. Min Act: -0.1700

Data Index: 2540759 (Open Web Text)

Max Activating Token Index: 118

Text #14

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.2983. Min Act: -0.1700

Data Index: 8676650 (Open Web Text)

Max Activating Token Index: 1008

Text #15

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3092. Min Act: -0.1700

Data Index: 6542185 (Open Web Text)

Max Activating Token Index: 885

Text #16

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.2940. Min Act: -0.1700

Data Index: 8573068 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3020. Min Act: -0.1700

Data Index: 5653726 (Open Web Text)

Max Activating Token Index: 304

Text #18

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.3277. Min Act: -0.1700

Data Index: 8497208 (Open Web Text)

Max Activating Token Index: 585

Text #19

Max Range: 5.7053. Min Range: -5.7053

Max Act: 5.2485. Min Act: -0.1700

Data Index: 6617466 (Open Web Text)

Max Activating Token Index: 466