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

Dataset: Open Web Text

Neuron 1566 in Layer 3

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: 4.0973. Min Range: -4.0973

Max Act: 4.0973. Min Act: -0.1700

Data Index: 872301 (Open Web Text)

Max Activating Token Index: 235

Text #1

Max Range: 4.0973. Min Range: -4.0973

Max Act: 4.0160. Min Act: -0.1700

Data Index: 4225337 (Open Web Text)

Max Activating Token Index: 764

Text #2

Max Range: 4.0973. Min Range: -4.0973

Max Act: 4.0156. Min Act: -0.1700

Data Index: 5607394 (Open Web Text)

Max Activating Token Index: 159

Text #3

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.9205. Min Act: -0.1700

Data Index: 4970348 (Open Web Text)

Max Activating Token Index: 28

Text #4

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.9472. Min Act: -0.1700

Data Index: 5456357 (Open Web Text)

Max Activating Token Index: 217

Text #5

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.9108. Min Act: -0.1700

Data Index: 4654229 (Open Web Text)

Max Activating Token Index: 541

Text #6

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8993. Min Act: -0.1700

Data Index: 8716520 (Open Web Text)

Max Activating Token Index: 256

Text #7

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8850. Min Act: -0.1700

Data Index: 2423960 (Open Web Text)

Max Activating Token Index: 841

Text #8

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8747. Min Act: -0.1700

Data Index: 2222598 (Open Web Text)

Max Activating Token Index: 902

Text #9

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8628. Min Act: -0.1700

Data Index: 4091679 (Open Web Text)

Max Activating Token Index: 255

Text #10

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8247. Min Act: -0.1700

Data Index: 3626789 (Open Web Text)

Max Activating Token Index: 527

Text #11

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8310. Min Act: -0.1700

Data Index: 6375970 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8534. Min Act: -0.1700

Data Index: 8326461 (Open Web Text)

Max Activating Token Index: 308

Text #13

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8200. Min Act: -0.1700

Data Index: 7137857 (Open Web Text)

Max Activating Token Index: 849

Text #14

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8295. Min Act: -0.1700

Data Index: 6414119 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8396. Min Act: -0.1700

Data Index: 596483 (Open Web Text)

Max Activating Token Index: 836

Text #16

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8182. Min Act: -0.1700

Data Index: 4104233 (Open Web Text)

Max Activating Token Index: 936

Text #17

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.7956. Min Act: -0.1700

Data Index: 900057 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.8026. Min Act: -0.1700

Data Index: 85563 (Open Web Text)

Max Activating Token Index: 389

Text #19

Max Range: 4.0973. Min Range: -4.0973

Max Act: 3.7932. Min Act: -0.1700

Data Index: 3141473 (Open Web Text)

Max Activating Token Index: 909