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

Dataset: Open Web Text

Neuron 1301 in Layer 0

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: 1.5434. Min Range: -1.5434

Max Act: 1.5434. Min Act: -0.1684

Data Index: 451672 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.4359. Min Act: -0.1681

Data Index: 3852921 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.4091. Min Act: -0.1604

Data Index: 3368294 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3872. Min Act: -0.1596

Data Index: 4703550 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3830. Min Act: -0.1638

Data Index: 4714080 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3830. Min Act: -0.1578

Data Index: 3171090 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3615. Min Act: -0.1183

Data Index: 7518083 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3638. Min Act: -0.1671

Data Index: 682137 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3659. Min Act: -0.1450

Data Index: 8297239 (Open Web Text)

Max Activating Token Index: 354

Text #9

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3574. Min Act: -0.1668

Data Index: 3599300 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3550. Min Act: -0.1657

Data Index: 6052380 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3464. Min Act: -0.1588

Data Index: 6986333 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3494. Min Act: -0.1565

Data Index: 5591660 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3393. Min Act: -0.1671

Data Index: 831423 (Open Web Text)

Max Activating Token Index: 985

Text #14

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3423. Min Act: -0.1298

Data Index: 6678228 (Open Web Text)

Max Activating Token Index: 954

Text #15

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3450. Min Act: -0.1588

Data Index: 7763232 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3313. Min Act: -0.1449

Data Index: 2654252 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3352. Min Act: -0.1699

Data Index: 2004960 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3245. Min Act: -0.1663

Data Index: 607289 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.5434. Min Range: -1.5434

Max Act: 1.3320. Min Act: -0.1411

Data Index: 7003380 (Open Web Text)

Max Activating Token Index: 1023