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

Dataset: Open Web Text

Neuron 2558 in Layer 3

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: 3.3551. Min Range: -3.3551

Max Act: 3.3551. Min Act: -0.1700

Data Index: 4237550 (Open Web Text)

Max Activating Token Index: 72

Text #1

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.3449. Min Act: -0.1700

Data Index: 3196958 (Open Web Text)

Max Activating Token Index: 706

Text #2

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2964. Min Act: -0.1700

Data Index: 1435938 (Open Web Text)

Max Activating Token Index: 774

Text #3

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2401. Min Act: -0.1700

Data Index: 6552805 (Open Web Text)

Max Activating Token Index: 718

Text #4

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2487. Min Act: -0.1700

Data Index: 4201560 (Open Web Text)

Max Activating Token Index: 103

Text #5

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2277. Min Act: -0.1700

Data Index: 6187536 (Open Web Text)

Max Activating Token Index: 762

Text #6

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2351. Min Act: -0.1700

Data Index: 7114188 (Open Web Text)

Max Activating Token Index: 452

Text #7

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2231. Min Act: -0.1700

Data Index: 5682608 (Open Web Text)

Max Activating Token Index: 135

Text #8

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2273. Min Act: -0.1700

Data Index: 5426552 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2138. Min Act: -0.1700

Data Index: 2010548 (Open Web Text)

Max Activating Token Index: 274

Text #10

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2347. Min Act: -0.1700

Data Index: 8609959 (Open Web Text)

Max Activating Token Index: 968

Text #11

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2086. Min Act: -0.1700

Data Index: 762299 (Open Web Text)

Max Activating Token Index: 82

Text #12

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1780. Min Act: -0.1700

Data Index: 4237549 (Open Web Text)

Max Activating Token Index: 314

Text #13

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1742. Min Act: -0.1700

Data Index: 1540278 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1638. Min Act: -0.1700

Data Index: 5157471 (Open Web Text)

Max Activating Token Index: 123

Text #15

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1730. Min Act: -0.1700

Data Index: 7836888 (Open Web Text)

Max Activating Token Index: 618

Text #16

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1755. Min Act: -0.1700

Data Index: 868386 (Open Web Text)

Max Activating Token Index: 771

Text #17

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1371. Min Act: -0.1700

Data Index: 1663864 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1406. Min Act: -0.1700

Data Index: 3931122 (Open Web Text)

Max Activating Token Index: 869

Text #19

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1276. Min Act: -0.1700

Data Index: 4316201 (Open Web Text)

Max Activating Token Index: 717