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

Dataset: Open Web Text

Neuron 1454 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: 4.2972. Min Range: -4.2972

Max Act: 4.2972. Min Act: -0.1700

Data Index: 5868814 (Open Web Text)

Max Activating Token Index: 472

Text #1

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.7656. Min Act: -0.1700

Data Index: 7157781 (Open Web Text)

Max Activating Token Index: 747

Text #2

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.5624. Min Act: -0.1700

Data Index: 4840681 (Open Web Text)

Max Activating Token Index: 128

Text #3

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.5200. Min Act: -0.1700

Data Index: 281168 (Open Web Text)

Max Activating Token Index: 774

Text #4

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.4923. Min Act: -0.1700

Data Index: 3925693 (Open Web Text)

Max Activating Token Index: 867

Text #5

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.5052. Min Act: -0.1700

Data Index: 676010 (Open Web Text)

Max Activating Token Index: 410

Text #6

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.4412. Min Act: -0.1700

Data Index: 3529022 (Open Web Text)

Max Activating Token Index: 641

Text #7

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.3683. Min Act: -0.1700

Data Index: 3375879 (Open Web Text)

Max Activating Token Index: 108

Text #8

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.3613. Min Act: -0.1700

Data Index: 1483035 (Open Web Text)

Max Activating Token Index: 630

Text #9

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.3894. Min Act: -0.1700

Data Index: 107582 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.3664. Min Act: -0.1700

Data Index: 1769384 (Open Web Text)

Max Activating Token Index: 320

Text #11

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.4066. Min Act: -0.1700

Data Index: 2082435 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.3417. Min Act: -0.1700

Data Index: 3789776 (Open Web Text)

Max Activating Token Index: 274

Text #13

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.3712. Min Act: -0.1700

Data Index: 8018322 (Open Web Text)

Max Activating Token Index: 143

Text #14

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1253446 (Open Web Text)

Max Activating Token Index: 728

Text #15

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.3295. Min Act: -0.1700

Data Index: 2398211 (Open Web Text)

Max Activating Token Index: 215

Text #16

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.2509. Min Act: -0.1700

Data Index: 3919128 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.3012. Min Act: -0.1700

Data Index: 6337031 (Open Web Text)

Max Activating Token Index: 864

Text #18

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.2814. Min Act: -0.1700

Data Index: 653438 (Open Web Text)

Max Activating Token Index: 326

Text #19

Max Range: 4.2972. Min Range: -4.2972

Max Act: 3.3026. Min Act: -0.1700

Data Index: 3558584 (Open Web Text)

Max Activating Token Index: 270