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

Dataset: Open Web Text

Neuron 2705 in Layer 1

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: 0.5705. Min Range: -0.5705

Max Act: 0.5653. Min Act: -0.1700

Data Index: 7820565 (Open Web Text)

Max Activating Token Index: 318

Text #1

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5705. Min Act: -0.1700

Data Index: 3123952 (Open Web Text)

Max Activating Token Index: 968

Text #2

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5604. Min Act: -0.1700

Data Index: 8281369 (Open Web Text)

Max Activating Token Index: 976

Text #3

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5517. Min Act: -0.1700

Data Index: 8222715 (Open Web Text)

Max Activating Token Index: 978

Text #4

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5588. Min Act: -0.1700

Data Index: 6477179 (Open Web Text)

Max Activating Token Index: 966

Text #5

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5533. Min Act: -0.1700

Data Index: 6942324 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5545. Min Act: -0.1700

Data Index: 6462516 (Open Web Text)

Max Activating Token Index: 968

Text #7

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5558. Min Act: -0.1700

Data Index: 44654 (Open Web Text)

Max Activating Token Index: 52

Text #8

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5452. Min Act: -0.1700

Data Index: 1874230 (Open Web Text)

Max Activating Token Index: 951

Text #9

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5530. Min Act: -0.1700

Data Index: 1389781 (Open Web Text)

Max Activating Token Index: 970

Text #10

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5440. Min Act: -0.1700

Data Index: 263538 (Open Web Text)

Max Activating Token Index: 957

Text #11

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5511. Min Act: -0.1700

Data Index: 2261080 (Open Web Text)

Max Activating Token Index: 974

Text #12

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5393. Min Act: -0.1700

Data Index: 4363345 (Open Web Text)

Max Activating Token Index: 957

Text #13

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5447. Min Act: -0.1700

Data Index: 4766220 (Open Web Text)

Max Activating Token Index: 964

Text #14

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5334. Min Act: -0.1700

Data Index: 5299195 (Open Web Text)

Max Activating Token Index: 958

Text #15

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5505. Min Act: -0.1700

Data Index: 5546829 (Open Web Text)

Max Activating Token Index: 968

Text #16

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5464. Min Act: -0.1700

Data Index: 5877643 (Open Web Text)

Max Activating Token Index: 977

Text #17

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5450. Min Act: -0.1700

Data Index: 6126160 (Open Web Text)

Max Activating Token Index: 968

Text #18

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5377. Min Act: -0.1700

Data Index: 6174906 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5389. Min Act: -0.1700

Data Index: 580014 (Open Web Text)

Max Activating Token Index: 2