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

Dataset: Open Web Text

Neuron 662 in Layer 4

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: 4.3076. Min Range: -4.3076

Max Act: 4.3076. Min Act: -0.1700

Data Index: 6071741 (Open Web Text)

Max Activating Token Index: 203

Text #1

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2286. Min Act: -0.1700

Data Index: 2127688 (Open Web Text)

Max Activating Token Index: 252

Text #2

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2094. Min Act: -0.1700

Data Index: 8704720 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2273. Min Act: -0.1700

Data Index: 7490467 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.2090. Min Act: -0.1700

Data Index: 5707420 (Open Web Text)

Max Activating Token Index: 302

Text #5

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1674. Min Act: -0.1700

Data Index: 388461 (Open Web Text)

Max Activating Token Index: 215

Text #6

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1852. Min Act: -0.1700

Data Index: 4956092 (Open Web Text)

Max Activating Token Index: 770

Text #7

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1248. Min Act: -0.1700

Data Index: 7397131 (Open Web Text)

Max Activating Token Index: 902

Text #8

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1335. Min Act: -0.1700

Data Index: 2854071 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1151. Min Act: -0.1700

Data Index: 7081279 (Open Web Text)

Max Activating Token Index: 299

Text #10

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1502. Min Act: -0.1700

Data Index: 5801069 (Open Web Text)

Max Activating Token Index: 786

Text #11

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1455. Min Act: -0.1700

Data Index: 4990742 (Open Web Text)

Max Activating Token Index: 576

Text #12

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1276. Min Act: -0.1700

Data Index: 97368 (Open Web Text)

Max Activating Token Index: 714

Text #13

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1199. Min Act: -0.1700

Data Index: 8612301 (Open Web Text)

Max Activating Token Index: 726

Text #14

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1270. Min Act: -0.1700

Data Index: 2812891 (Open Web Text)

Max Activating Token Index: 599

Text #15

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1140. Min Act: -0.1700

Data Index: 4495497 (Open Web Text)

Max Activating Token Index: 768

Text #16

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.0822. Min Act: -0.1700

Data Index: 6411787 (Open Web Text)

Max Activating Token Index: 507

Text #17

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.0649. Min Act: -0.1700

Data Index: 461064 (Open Web Text)

Max Activating Token Index: 853

Text #18

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.1071. Min Act: -0.1700

Data Index: 2403566 (Open Web Text)

Max Activating Token Index: 918

Text #19

Max Range: 4.3076. Min Range: -4.3076

Max Act: 4.0446. Min Act: -0.1700

Data Index: 2806604 (Open Web Text)

Max Activating Token Index: 898