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

Dataset: Open Web Text

Neuron 679 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: 4.7484. Min Range: -4.7484

Max Act: 4.7484. Min Act: -0.1700

Data Index: 3224966 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.7440. Min Act: -0.1700

Data Index: 312853 (Open Web Text)

Max Activating Token Index: 521

Text #2

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.6726. Min Act: -0.1700

Data Index: 808612 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.6660. Min Act: -0.1700

Data Index: 6886643 (Open Web Text)

Max Activating Token Index: 270

Text #4

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.6472. Min Act: -0.1700

Data Index: 1998478 (Open Web Text)

Max Activating Token Index: 225

Text #5

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5987. Min Act: -0.1700

Data Index: 1821114 (Open Web Text)

Max Activating Token Index: 373

Text #6

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.6361. Min Act: -0.1700

Data Index: 4495842 (Open Web Text)

Max Activating Token Index: 36

Text #7

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.6005. Min Act: -0.1700

Data Index: 358878 (Open Web Text)

Max Activating Token Index: 167

Text #8

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5814. Min Act: -0.1700

Data Index: 5763971 (Open Web Text)

Max Activating Token Index: 289

Text #9

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5752. Min Act: -0.1700

Data Index: 4365109 (Open Web Text)

Max Activating Token Index: 125

Text #10

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5404. Min Act: -0.1700

Data Index: 3380768 (Open Web Text)

Max Activating Token Index: 988

Text #11

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5522. Min Act: -0.1700

Data Index: 7000538 (Open Web Text)

Max Activating Token Index: 174

Text #12

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5430. Min Act: -0.1700

Data Index: 1900624 (Open Web Text)

Max Activating Token Index: 675

Text #13

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5234. Min Act: -0.1700

Data Index: 7958104 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5120. Min Act: -0.1700

Data Index: 8538110 (Open Web Text)

Max Activating Token Index: 654

Text #15

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5423. Min Act: -0.1700

Data Index: 5125313 (Open Web Text)

Max Activating Token Index: 317

Text #16

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5358. Min Act: -0.1700

Data Index: 4173537 (Open Web Text)

Max Activating Token Index: 122

Text #17

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5332. Min Act: -0.1700

Data Index: 6562660 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5268. Min Act: -0.1700

Data Index: 4409813 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 4.7484. Min Range: -4.7484

Max Act: 4.5013. Min Act: -0.1700

Data Index: 2554494 (Open Web Text)

Max Activating Token Index: 72