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

Dataset: Open Web Text

Neuron 1257 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: 3.3809. Min Range: -3.3809

Max Act: 3.3809. Min Act: -0.1700

Data Index: 5747352 (Open Web Text)

Max Activating Token Index: 838

Text #1

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.3585. Min Act: -0.1700

Data Index: 7581192 (Open Web Text)

Max Activating Token Index: 458

Text #2

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.3713. Min Act: -0.1700

Data Index: 5461 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.3336. Min Act: -0.1700

Data Index: 1389218 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.3319. Min Act: -0.1700

Data Index: 4273542 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2828. Min Act: -0.1700

Data Index: 114737 (Open Web Text)

Max Activating Token Index: 172

Text #6

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2947. Min Act: -0.1700

Data Index: 1583293 (Open Web Text)

Max Activating Token Index: 259

Text #7

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2712. Min Act: -0.1700

Data Index: 958508 (Open Web Text)

Max Activating Token Index: 870

Text #8

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2601. Min Act: -0.1700

Data Index: 154721 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2669. Min Act: -0.1700

Data Index: 3462777 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2691. Min Act: -0.1700

Data Index: 5880110 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2768. Min Act: -0.1700

Data Index: 4303008 (Open Web Text)

Max Activating Token Index: 694

Text #12

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2302. Min Act: -0.1700

Data Index: 7042298 (Open Web Text)

Max Activating Token Index: 599

Text #13

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2615. Min Act: -0.1700

Data Index: 2477322 (Open Web Text)

Max Activating Token Index: 419

Text #14

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2496. Min Act: -0.1700

Data Index: 7628121 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2125. Min Act: -0.1700

Data Index: 7872673 (Open Web Text)

Max Activating Token Index: 524

Text #16

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2017. Min Act: -0.1700

Data Index: 7265203 (Open Web Text)

Max Activating Token Index: 615

Text #17

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2371. Min Act: -0.1700

Data Index: 2441404 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2254. Min Act: -0.1700

Data Index: 4083632 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2329. Min Act: -0.1700

Data Index: 2385658 (Open Web Text)

Max Activating Token Index: 445