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

Dataset: Open Web Text

Neuron 1635 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: 0.6514. Min Range: -0.6514

Max Act: 0.6492. Min Act: -0.1700

Data Index: 4526292 (Open Web Text)

Max Activating Token Index: 49

Text #1

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6479. Min Act: -0.1700

Data Index: 6641842 (Open Web Text)

Max Activating Token Index: 64

Text #2

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6514. Min Act: -0.1700

Data Index: 2971566 (Open Web Text)

Max Activating Token Index: 66

Text #3

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6464. Min Act: -0.1700

Data Index: 8733537 (Open Web Text)

Max Activating Token Index: 72

Text #4

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6430. Min Act: -0.1700

Data Index: 5721603 (Open Web Text)

Max Activating Token Index: 72

Text #5

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6384. Min Act: -0.1700

Data Index: 2636511 (Open Web Text)

Max Activating Token Index: 79

Text #6

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6344. Min Act: -0.1700

Data Index: 6172630 (Open Web Text)

Max Activating Token Index: 68

Text #7

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6426. Min Act: -0.1700

Data Index: 3135250 (Open Web Text)

Max Activating Token Index: 63

Text #8

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6413. Min Act: -0.1700

Data Index: 8635269 (Open Web Text)

Max Activating Token Index: 71

Text #9

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6514. Min Act: -0.1700

Data Index: 6774331 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6354. Min Act: -0.1700

Data Index: 3643709 (Open Web Text)

Max Activating Token Index: 61

Text #11

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6353. Min Act: -0.1700

Data Index: 697428 (Open Web Text)

Max Activating Token Index: 64

Text #12

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6348. Min Act: -0.1700

Data Index: 1590040 (Open Web Text)

Max Activating Token Index: 61

Text #13

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6197. Min Act: -0.1700

Data Index: 58145 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6310. Min Act: -0.1700

Data Index: 2096311 (Open Web Text)

Max Activating Token Index: 57

Text #15

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6219. Min Act: -0.1700

Data Index: 3809082 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6263. Min Act: -0.1700

Data Index: 4435795 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6190. Min Act: -0.1699

Data Index: 6730381 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6240. Min Act: -0.1700

Data Index: 6747058 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6251. Min Act: -0.1700

Data Index: 2491785 (Open Web Text)

Max Activating Token Index: 68