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

Dataset: Open Web Text

Neuron 91 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: 2.8802. Min Range: -2.8802

Max Act: 2.8802. Min Act: -0.1700

Data Index: 7176993 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.8037. Min Act: -0.1700

Data Index: 5330134 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7942. Min Act: -0.1700

Data Index: 1040511 (Open Web Text)

Max Activating Token Index: 949

Text #3

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7736. Min Act: -0.1700

Data Index: 4229998 (Open Web Text)

Max Activating Token Index: 694

Text #4

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7776. Min Act: -0.1700

Data Index: 7520398 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7590. Min Act: -0.1700

Data Index: 3804998 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7265. Min Act: -0.1700

Data Index: 5987992 (Open Web Text)

Max Activating Token Index: 281

Text #7

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7322. Min Act: -0.1700

Data Index: 8379669 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7314. Min Act: -0.1700

Data Index: 6854138 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7257. Min Act: -0.1700

Data Index: 7677066 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7319. Min Act: -0.1700

Data Index: 4427583 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7289. Min Act: -0.1700

Data Index: 6242360 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7330. Min Act: -0.1700

Data Index: 1040512 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7436. Min Act: -0.1700

Data Index: 5154507 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7161. Min Act: -0.1700

Data Index: 6241389 (Open Web Text)

Max Activating Token Index: 112

Text #15

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7220. Min Act: -0.1700

Data Index: 1806779 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7209. Min Act: -0.1700

Data Index: 2196254 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7224. Min Act: -0.1700

Data Index: 4223507 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7150. Min Act: -0.1700

Data Index: 85421 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.7124. Min Act: -0.1700

Data Index: 6723615 (Open Web Text)

Max Activating Token Index: 841