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

Dataset: Open Web Text

Neuron 2192 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: 3.9674. Min Range: -3.9674

Max Act: 3.9674. Min Act: -0.1700

Data Index: 503518 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.9130. Min Act: -0.1700

Data Index: 8079065 (Open Web Text)

Max Activating Token Index: 955

Text #2

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.8525. Min Act: -0.1700

Data Index: 4446105 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.8685. Min Act: -0.1700

Data Index: 8054736 (Open Web Text)

Max Activating Token Index: 951

Text #4

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.8205. Min Act: -0.1700

Data Index: 3626310 (Open Web Text)

Max Activating Token Index: 326

Text #5

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7975. Min Act: -0.1700

Data Index: 7415332 (Open Web Text)

Max Activating Token Index: 671

Text #6

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.8187. Min Act: -0.1700

Data Index: 2601190 (Open Web Text)

Max Activating Token Index: 219

Text #7

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7988. Min Act: -0.1700

Data Index: 3500716 (Open Web Text)

Max Activating Token Index: 41

Text #8

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7652. Min Act: -0.1700

Data Index: 2633615 (Open Web Text)

Max Activating Token Index: 801

Text #9

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7783. Min Act: -0.1700

Data Index: 8587176 (Open Web Text)

Max Activating Token Index: 456

Text #10

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7868. Min Act: -0.1700

Data Index: 7097268 (Open Web Text)

Max Activating Token Index: 158

Text #11

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7652. Min Act: -0.1700

Data Index: 558090 (Open Web Text)

Max Activating Token Index: 619

Text #12

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7450. Min Act: -0.1700

Data Index: 596776 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7467. Min Act: -0.1700

Data Index: 7371040 (Open Web Text)

Max Activating Token Index: 796

Text #14

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7624. Min Act: -0.1700

Data Index: 689203 (Open Web Text)

Max Activating Token Index: 319

Text #15

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7509. Min Act: -0.1700

Data Index: 2336411 (Open Web Text)

Max Activating Token Index: 617

Text #16

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7461. Min Act: -0.1700

Data Index: 2982912 (Open Web Text)

Max Activating Token Index: 343

Text #17

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7612. Min Act: -0.1700

Data Index: 5238462 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7502. Min Act: -0.1700

Data Index: 1457432 (Open Web Text)

Max Activating Token Index: 130

Text #19

Max Range: 3.9674. Min Range: -3.9674

Max Act: 3.7245. Min Act: -0.1700

Data Index: 4127373 (Open Web Text)

Max Activating Token Index: 692