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

Dataset: Open Web Text

Neuron 1960 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: 1.7424. Min Range: -1.7424

Max Act: 1.7405. Min Act: -0.1700

Data Index: 6456173 (Open Web Text)

Max Activating Token Index: 651

Text #1

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7424. Min Act: -0.1700

Data Index: 3311239 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7363. Min Act: -0.1700

Data Index: 7817740 (Open Web Text)

Max Activating Token Index: 56

Text #3

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7297. Min Act: -0.1700

Data Index: 1928184 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7253. Min Act: -0.1700

Data Index: 99877 (Open Web Text)

Max Activating Token Index: 73

Text #5

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7257. Min Act: -0.1700

Data Index: 7047321 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7313. Min Act: -0.1700

Data Index: 7249429 (Open Web Text)

Max Activating Token Index: 75

Text #7

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7127. Min Act: -0.1700

Data Index: 7807357 (Open Web Text)

Max Activating Token Index: 664

Text #8

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6982. Min Act: -0.1700

Data Index: 8048693 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6799. Min Act: -0.1700

Data Index: 7103219 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6709. Min Act: -0.1700

Data Index: 6723398 (Open Web Text)

Max Activating Token Index: 716

Text #11

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6608. Min Act: -0.1700

Data Index: 4138646 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6539. Min Act: -0.1700

Data Index: 2591851 (Open Web Text)

Max Activating Token Index: 51

Text #13

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6589. Min Act: -0.1700

Data Index: 7214666 (Open Web Text)

Max Activating Token Index: 98

Text #14

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6556. Min Act: -0.1700

Data Index: 8735309 (Open Web Text)

Max Activating Token Index: 375

Text #15

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6465. Min Act: -0.1700

Data Index: 810415 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6459. Min Act: -0.1700

Data Index: 3565653 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6426. Min Act: -0.1700

Data Index: 1190597 (Open Web Text)

Max Activating Token Index: 29

Text #18

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6278. Min Act: -0.1700

Data Index: 5544341 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6312. Min Act: -0.1700

Data Index: 5299532 (Open Web Text)

Max Activating Token Index: 457