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

Dataset: Open Web Text

Neuron 925 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: 4.0597. Min Range: -4.0597

Max Act: 4.0448. Min Act: -0.1700

Data Index: 7032987 (Open Web Text)

Max Activating Token Index: 157

Text #1

Max Range: 4.0597. Min Range: -4.0597

Max Act: 4.0597. Min Act: -0.1700

Data Index: 2242414 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 4.0597. Min Range: -4.0597

Max Act: 4.0060. Min Act: -0.1700

Data Index: 1953047 (Open Web Text)

Max Activating Token Index: 401

Text #3

Max Range: 4.0597. Min Range: -4.0597

Max Act: 4.0002. Min Act: -0.1700

Data Index: 2589684 (Open Web Text)

Max Activating Token Index: 362

Text #4

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.9783. Min Act: -0.1700

Data Index: 1900836 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.9758. Min Act: -0.1700

Data Index: 1643505 (Open Web Text)

Max Activating Token Index: 313

Text #6

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.9431. Min Act: -0.1700

Data Index: 7311274 (Open Web Text)

Max Activating Token Index: 117

Text #7

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.9496. Min Act: -0.1700

Data Index: 7028897 (Open Web Text)

Max Activating Token Index: 251

Text #8

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.9633. Min Act: -0.1700

Data Index: 7569540 (Open Web Text)

Max Activating Token Index: 113

Text #9

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.9513. Min Act: -0.1700

Data Index: 7799311 (Open Web Text)

Max Activating Token Index: 142

Text #10

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.9592. Min Act: -0.1700

Data Index: 4014977 (Open Web Text)

Max Activating Token Index: 890

Text #11

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.9336. Min Act: -0.1700

Data Index: 7386536 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.9198. Min Act: -0.1700

Data Index: 3700619 (Open Web Text)

Max Activating Token Index: 507

Text #13

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.9173. Min Act: -0.1700

Data Index: 461991 (Open Web Text)

Max Activating Token Index: 892

Text #14

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.8911. Min Act: -0.1700

Data Index: 1851743 (Open Web Text)

Max Activating Token Index: 904

Text #15

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.8775. Min Act: -0.1700

Data Index: 4140030 (Open Web Text)

Max Activating Token Index: 547

Text #16

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.8638. Min Act: -0.1700

Data Index: 6762492 (Open Web Text)

Max Activating Token Index: 729

Text #17

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.8250. Min Act: -0.1700

Data Index: 3888190 (Open Web Text)

Max Activating Token Index: 152

Text #18

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.8964. Min Act: -0.1700

Data Index: 4617401 (Open Web Text)

Max Activating Token Index: 741

Text #19

Max Range: 4.0597. Min Range: -4.0597

Max Act: 3.8078. Min Act: -0.1700

Data Index: 3822255 (Open Web Text)

Max Activating Token Index: 745