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

Dataset: Open Web Text

Neuron 2911 in Layer 5

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: 5.1365. Min Range: -5.1365

Max Act: 5.1008. Min Act: -0.1700

Data Index: 6602964 (Open Web Text)

Max Activating Token Index: 423

Text #1

Max Range: 5.1365. Min Range: -5.1365

Max Act: 5.1365. Min Act: -0.1700

Data Index: 8104079 (Open Web Text)

Max Activating Token Index: 631

Text #2

Max Range: 5.1365. Min Range: -5.1365

Max Act: 5.1211. Min Act: -0.1700

Data Index: 5839211 (Open Web Text)

Max Activating Token Index: 417

Text #3

Max Range: 5.1365. Min Range: -5.1365

Max Act: 5.0296. Min Act: -0.1700

Data Index: 7502664 (Open Web Text)

Max Activating Token Index: 984

Text #4

Max Range: 5.1365. Min Range: -5.1365

Max Act: 5.0002. Min Act: -0.1700

Data Index: 5075917 (Open Web Text)

Max Activating Token Index: 930

Text #5

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9589. Min Act: -0.1700

Data Index: 7388758 (Open Web Text)

Max Activating Token Index: 656

Text #6

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9510. Min Act: -0.1700

Data Index: 7520155 (Open Web Text)

Max Activating Token Index: 946

Text #7

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9520. Min Act: -0.1700

Data Index: 5922575 (Open Web Text)

Max Activating Token Index: 985

Text #8

Max Range: 5.1365. Min Range: -5.1365

Max Act: 5.0391. Min Act: -0.1700

Data Index: 2746534 (Open Web Text)

Max Activating Token Index: 597

Text #9

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9603. Min Act: -0.1700

Data Index: 7423034 (Open Web Text)

Max Activating Token Index: 414

Text #10

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9741. Min Act: -0.1700

Data Index: 2612339 (Open Web Text)

Max Activating Token Index: 995

Text #11

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9191. Min Act: -0.1700

Data Index: 5304975 (Open Web Text)

Max Activating Token Index: 238

Text #12

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9344. Min Act: -0.1700

Data Index: 934852 (Open Web Text)

Max Activating Token Index: 491

Text #13

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9066. Min Act: -0.1700

Data Index: 5766890 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9238. Min Act: -0.1700

Data Index: 8272845 (Open Web Text)

Max Activating Token Index: 842

Text #15

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9007. Min Act: -0.1700

Data Index: 7153453 (Open Web Text)

Max Activating Token Index: 626

Text #16

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.8777. Min Act: -0.1700

Data Index: 1731235 (Open Web Text)

Max Activating Token Index: 565

Text #17

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.8975. Min Act: -0.1700

Data Index: 8147618 (Open Web Text)

Max Activating Token Index: 562

Text #18

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.8766. Min Act: -0.1700

Data Index: 3500746 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.8994. Min Act: -0.1700

Data Index: 847527 (Open Web Text)

Max Activating Token Index: 542