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

Dataset: Open Web Text

Neuron 2598 in Layer 6

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: 4.5531. Min Range: -4.5531

Max Act: 4.5531. Min Act: -0.1700

Data Index: 1922450 (Open Web Text)

Max Activating Token Index: 274

Text #1

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.4388. Min Act: -0.1700

Data Index: 5645678 (Open Web Text)

Max Activating Token Index: 448

Text #2

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.4365. Min Act: -0.1700

Data Index: 5912096 (Open Web Text)

Max Activating Token Index: 717

Text #3

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.4509. Min Act: -0.1700

Data Index: 6571079 (Open Web Text)

Max Activating Token Index: 494

Text #4

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.4458. Min Act: -0.1700

Data Index: 3822470 (Open Web Text)

Max Activating Token Index: 188

Text #5

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.4191. Min Act: -0.1700

Data Index: 8424101 (Open Web Text)

Max Activating Token Index: 239

Text #6

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.4209. Min Act: -0.1700

Data Index: 8304671 (Open Web Text)

Max Activating Token Index: 479

Text #7

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3730. Min Act: -0.1700

Data Index: 4846154 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3700. Min Act: -0.1700

Data Index: 8654555 (Open Web Text)

Max Activating Token Index: 625

Text #9

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3711. Min Act: -0.1700

Data Index: 7570233 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3767. Min Act: -0.1700

Data Index: 1347038 (Open Web Text)

Max Activating Token Index: 709

Text #11

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.4066. Min Act: -0.1700

Data Index: 1519360 (Open Web Text)

Max Activating Token Index: 206

Text #12

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3567. Min Act: -0.1700

Data Index: 131474 (Open Web Text)

Max Activating Token Index: 987

Text #13

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3780. Min Act: -0.1700

Data Index: 7348544 (Open Web Text)

Max Activating Token Index: 246

Text #14

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3501. Min Act: -0.1700

Data Index: 1212053 (Open Web Text)

Max Activating Token Index: 782

Text #15

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3345. Min Act: -0.1700

Data Index: 6912454 (Open Web Text)

Max Activating Token Index: 854

Text #16

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3641. Min Act: -0.1700

Data Index: 6910103 (Open Web Text)

Max Activating Token Index: 262

Text #17

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3703. Min Act: -0.1700

Data Index: 481896 (Open Web Text)

Max Activating Token Index: 398

Text #18

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3411. Min Act: -0.1700

Data Index: 5974516 (Open Web Text)

Max Activating Token Index: 536

Text #19

Max Range: 4.5531. Min Range: -4.5531

Max Act: 4.3464. Min Act: -0.1700

Data Index: 2018803 (Open Web Text)

Max Activating Token Index: 916