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

Dataset: Open Web Text

Neuron 786 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: 5.7028. Min Range: -5.7028

Max Act: 5.7028. Min Act: -0.1700

Data Index: 7188429 (Open Web Text)

Max Activating Token Index: 624

Text #1

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.6251. Min Act: -0.1700

Data Index: 3596573 (Open Web Text)

Max Activating Token Index: 221

Text #2

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.6057. Min Act: -0.1700

Data Index: 7016324 (Open Web Text)

Max Activating Token Index: 850

Text #3

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.5542. Min Act: -0.1700

Data Index: 2351250 (Open Web Text)

Max Activating Token Index: 512

Text #4

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.5513. Min Act: -0.1700

Data Index: 8652651 (Open Web Text)

Max Activating Token Index: 317

Text #5

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.5486. Min Act: -0.1700

Data Index: 832096 (Open Web Text)

Max Activating Token Index: 628

Text #6

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4906. Min Act: -0.1700

Data Index: 5962972 (Open Web Text)

Max Activating Token Index: 121

Text #7

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4708. Min Act: -0.1700

Data Index: 27229 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4440. Min Act: -0.1700

Data Index: 915635 (Open Web Text)

Max Activating Token Index: 790

Text #9

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4825. Min Act: -0.1700

Data Index: 8420004 (Open Web Text)

Max Activating Token Index: 571

Text #10

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4646. Min Act: -0.1700

Data Index: 6368726 (Open Web Text)

Max Activating Token Index: 650

Text #11

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4352. Min Act: -0.1700

Data Index: 434051 (Open Web Text)

Max Activating Token Index: 637

Text #12

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4452. Min Act: -0.1700

Data Index: 1395585 (Open Web Text)

Max Activating Token Index: 81

Text #13

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4461. Min Act: -0.1700

Data Index: 2622220 (Open Web Text)

Max Activating Token Index: 594

Text #14

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4370. Min Act: -0.1700

Data Index: 2703681 (Open Web Text)

Max Activating Token Index: 422

Text #15

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4242. Min Act: -0.1700

Data Index: 1633201 (Open Web Text)

Max Activating Token Index: 72

Text #16

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4286. Min Act: -0.1700

Data Index: 426344 (Open Web Text)

Max Activating Token Index: 292

Text #17

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4429. Min Act: -0.1700

Data Index: 5328156 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4383. Min Act: -0.1700

Data Index: 3830705 (Open Web Text)

Max Activating Token Index: 217

Text #19

Max Range: 5.7028. Min Range: -5.7028

Max Act: 5.4195. Min Act: -0.1700

Data Index: 3478173 (Open Web Text)

Max Activating Token Index: 608