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

Dataset: Open Web Text

Neuron 1435 in Layer 4

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: 2.9507. Min Range: -2.9507

Max Act: 2.9507. Min Act: -0.1700

Data Index: 1469053 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.9507. Min Act: -0.1700

Data Index: 8317069 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.9507. Min Act: -0.1700

Data Index: 6894477 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.9507. Min Act: -0.1700

Data Index: 3108267 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.9507. Min Act: -0.1700

Data Index: 4628334 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.9507. Min Act: -0.1700

Data Index: 3230190 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.7444. Min Act: -0.1700

Data Index: 4778303 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.7326. Min Act: -0.1700

Data Index: 2127291 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6978. Min Act: -0.1700

Data Index: 3847231 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.7025. Min Act: -0.1700

Data Index: 6569384 (Open Web Text)

Max Activating Token Index: 786

Text #10

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6972. Min Act: -0.1700

Data Index: 1129247 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6629. Min Act: -0.1700

Data Index: 480460 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6551. Min Act: -0.1700

Data Index: 7339244 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6581. Min Act: -0.1700

Data Index: 386358 (Open Web Text)

Max Activating Token Index: 115

Text #14

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6494. Min Act: -0.1700

Data Index: 6349587 (Open Web Text)

Max Activating Token Index: 257

Text #15

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6552. Min Act: -0.1700

Data Index: 7736473 (Open Web Text)

Max Activating Token Index: 445

Text #16

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6579. Min Act: -0.1700

Data Index: 2200501 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6346. Min Act: -0.1700

Data Index: 7584104 (Open Web Text)

Max Activating Token Index: 438

Text #18

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6490. Min Act: -0.1700

Data Index: 3124448 (Open Web Text)

Max Activating Token Index: 710

Text #19

Max Range: 2.9507. Min Range: -2.9507

Max Act: 2.6398. Min Act: -0.1700

Data Index: 2907976 (Open Web Text)

Max Activating Token Index: 521