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

Dataset: Open Web Text

Neuron 254 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: 5.7539. Min Range: -5.7539

Max Act: 5.7539. Min Act: -0.1700

Data Index: 7144363 (Open Web Text)

Max Activating Token Index: 66

Text #1

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.6840. Min Act: -0.1699

Data Index: 2820720 (Open Web Text)

Max Activating Token Index: 878

Text #2

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.5656. Min Act: -0.1700

Data Index: 7545099 (Open Web Text)

Max Activating Token Index: 535

Text #3

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.4849. Min Act: -0.1700

Data Index: 3229765 (Open Web Text)

Max Activating Token Index: 904

Text #4

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.5394. Min Act: -0.1700

Data Index: 6993951 (Open Web Text)

Max Activating Token Index: 315

Text #5

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.4529. Min Act: -0.1700

Data Index: 1200688 (Open Web Text)

Max Activating Token Index: 277

Text #6

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.4391. Min Act: -0.1700

Data Index: 6306701 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.4983. Min Act: -0.1700

Data Index: 8139374 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.4208. Min Act: -0.1700

Data Index: 5710777 (Open Web Text)

Max Activating Token Index: 522

Text #9

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.4555. Min Act: -0.1700

Data Index: 3555168 (Open Web Text)

Max Activating Token Index: 576

Text #10

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.4199. Min Act: -0.1700

Data Index: 8478134 (Open Web Text)

Max Activating Token Index: 606

Text #11

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.4593. Min Act: -0.1700

Data Index: 8341327 (Open Web Text)

Max Activating Token Index: 226

Text #12

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.4023. Min Act: -0.1700

Data Index: 2055372 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.3629. Min Act: -0.1700

Data Index: 1251998 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.3726. Min Act: -0.1700

Data Index: 8649511 (Open Web Text)

Max Activating Token Index: 505

Text #15

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.4206. Min Act: -0.1700

Data Index: 3838286 (Open Web Text)

Max Activating Token Index: 909

Text #16

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.3533. Min Act: -0.1700

Data Index: 167953 (Open Web Text)

Max Activating Token Index: 759

Text #17

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.2903. Min Act: -0.1700

Data Index: 8141765 (Open Web Text)

Max Activating Token Index: 502

Text #18

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.3458. Min Act: -0.1700

Data Index: 5833070 (Open Web Text)

Max Activating Token Index: 74

Text #19

Max Range: 5.7539. Min Range: -5.7539

Max Act: 5.3446. Min Act: -0.1700

Data Index: 6545764 (Open Web Text)

Max Activating Token Index: 1019