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

Dataset: Open Web Text

Neuron 2547 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: 3.7587. Min Range: -3.7587

Max Act: 3.7587. Min Act: -0.1700

Data Index: 1312619 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.7154. Min Act: -0.1700

Data Index: 2979398 (Open Web Text)

Max Activating Token Index: 450

Text #2

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.7227. Min Act: -0.1700

Data Index: 7588987 (Open Web Text)

Max Activating Token Index: 364

Text #3

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.7094. Min Act: -0.1700

Data Index: 7319104 (Open Web Text)

Max Activating Token Index: 902

Text #4

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6821. Min Act: -0.1700

Data Index: 4950386 (Open Web Text)

Max Activating Token Index: 45

Text #5

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6944. Min Act: -0.1700

Data Index: 946950 (Open Web Text)

Max Activating Token Index: 412

Text #6

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6753. Min Act: -0.1700

Data Index: 3124558 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6816. Min Act: -0.1700

Data Index: 1949859 (Open Web Text)

Max Activating Token Index: 389

Text #8

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6673. Min Act: -0.1700

Data Index: 1377436 (Open Web Text)

Max Activating Token Index: 350

Text #9

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6543. Min Act: -0.1700

Data Index: 6574952 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6569. Min Act: -0.1700

Data Index: 3440566 (Open Web Text)

Max Activating Token Index: 104

Text #11

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6567. Min Act: -0.1700

Data Index: 4652618 (Open Web Text)

Max Activating Token Index: 784

Text #12

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6297. Min Act: -0.1700

Data Index: 7851885 (Open Web Text)

Max Activating Token Index: 1001

Text #13

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6428. Min Act: -0.1700

Data Index: 6230293 (Open Web Text)

Max Activating Token Index: 366

Text #14

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6419. Min Act: -0.1700

Data Index: 8272527 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6353. Min Act: -0.1700

Data Index: 3422097 (Open Web Text)

Max Activating Token Index: 53

Text #16

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6109. Min Act: -0.1700

Data Index: 3643233 (Open Web Text)

Max Activating Token Index: 835

Text #17

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6300. Min Act: -0.1700

Data Index: 6677318 (Open Web Text)

Max Activating Token Index: 407

Text #18

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6023. Min Act: -0.1700

Data Index: 4409996 (Open Web Text)

Max Activating Token Index: 732

Text #19

Max Range: 3.7587. Min Range: -3.7587

Max Act: 3.6220. Min Act: -0.1700

Data Index: 2018221 (Open Web Text)

Max Activating Token Index: 630