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

Dataset: Open Web Text

Neuron 1832 in Layer 3

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: 3.7711. Min Range: -3.7711

Max Act: 3.7711. Min Act: -0.1700

Data Index: 2490384 (Open Web Text)

Max Activating Token Index: 696

Text #1

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.7043. Min Act: -0.1700

Data Index: 4635911 (Open Web Text)

Max Activating Token Index: 717

Text #2

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.6520. Min Act: -0.1700

Data Index: 2693672 (Open Web Text)

Max Activating Token Index: 194

Text #3

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.6098. Min Act: -0.1700

Data Index: 7936022 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.5496. Min Act: -0.1700

Data Index: 5483576 (Open Web Text)

Max Activating Token Index: 512

Text #5

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.5040. Min Act: -0.1700

Data Index: 3645328 (Open Web Text)

Max Activating Token Index: 702

Text #6

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4640. Min Act: -0.1700

Data Index: 4783034 (Open Web Text)

Max Activating Token Index: 351

Text #7

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4832. Min Act: -0.1700

Data Index: 2562362 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4519. Min Act: -0.1700

Data Index: 2210768 (Open Web Text)

Max Activating Token Index: 800

Text #9

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4759. Min Act: -0.1700

Data Index: 8417012 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4942. Min Act: -0.1700

Data Index: 3645327 (Open Web Text)

Max Activating Token Index: 655

Text #11

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4332. Min Act: -0.1700

Data Index: 8724121 (Open Web Text)

Max Activating Token Index: 603

Text #12

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4384. Min Act: -0.1700

Data Index: 8329675 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4532. Min Act: -0.1700

Data Index: 6304697 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4313. Min Act: -0.1700

Data Index: 3272408 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4263. Min Act: -0.1700

Data Index: 7734236 (Open Web Text)

Max Activating Token Index: 563

Text #16

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.3988. Min Act: -0.1700

Data Index: 4159179 (Open Web Text)

Max Activating Token Index: 76

Text #17

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4137. Min Act: -0.1700

Data Index: 8158133 (Open Web Text)

Max Activating Token Index: 179

Text #18

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.4431. Min Act: -0.1700

Data Index: 781235 (Open Web Text)

Max Activating Token Index: 353

Text #19

Max Range: 3.7711. Min Range: -3.7711

Max Act: 3.3843. Min Act: -0.1700

Data Index: 6079845 (Open Web Text)

Max Activating Token Index: 183