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

Dataset: Open Web Text

Neuron 2694 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: 4.5524. Min Range: -4.5524

Max Act: 4.5524. Min Act: -0.1700

Data Index: 455632 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.4723. Min Act: -0.1700

Data Index: 7477677 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3998. Min Act: -0.1700

Data Index: 2081488 (Open Web Text)

Max Activating Token Index: 39

Text #3

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.4196. Min Act: -0.1700

Data Index: 455630 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3789. Min Act: -0.1700

Data Index: 5070920 (Open Web Text)

Max Activating Token Index: 26

Text #5

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3483. Min Act: -0.1700

Data Index: 5954254 (Open Web Text)

Max Activating Token Index: 760

Text #6

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3399. Min Act: -0.1700

Data Index: 6086112 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3391. Min Act: -0.1700

Data Index: 1276232 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3364. Min Act: -0.1700

Data Index: 2315401 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3254. Min Act: -0.1700

Data Index: 7332446 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3504. Min Act: -0.1700

Data Index: 2277475 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3280. Min Act: -0.1700

Data Index: 3070565 (Open Web Text)

Max Activating Token Index: 20

Text #12

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3200. Min Act: -0.1700

Data Index: 5886861 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3096. Min Act: -0.1700

Data Index: 1072533 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3182. Min Act: -0.1700

Data Index: 8776096 (Open Web Text)

Max Activating Token Index: 41

Text #15

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.2985. Min Act: -0.1700

Data Index: 8008944 (Open Web Text)

Max Activating Token Index: 549

Text #16

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.3136. Min Act: -0.1700

Data Index: 1398948 (Open Web Text)

Max Activating Token Index: 95

Text #17

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.2938. Min Act: -0.1700

Data Index: 2076370 (Open Web Text)

Max Activating Token Index: 50

Text #18

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.2819. Min Act: -0.1700

Data Index: 5552808 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 4.5524. Min Range: -4.5524

Max Act: 4.2807. Min Act: -0.1700

Data Index: 2174846 (Open Web Text)

Max Activating Token Index: 46