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

Dataset: Open Web Text

Neuron 3069 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: 5.9243. Min Range: -5.9243

Max Act: 5.9243. Min Act: -0.1700

Data Index: 3108245 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.9168. Min Act: -0.1700

Data Index: 1123983 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.9126. Min Act: -0.1700

Data Index: 4457672 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.8445. Min Act: -0.1700

Data Index: 4887665 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.8128. Min Act: -0.1700

Data Index: 4119847 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.8104. Min Act: -0.1700

Data Index: 2980808 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7943. Min Act: -0.1700

Data Index: 4606542 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.8150. Min Act: -0.1700

Data Index: 7159383 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.8067. Min Act: -0.1700

Data Index: 8783482 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.8118. Min Act: -0.1700

Data Index: 8516108 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7788. Min Act: -0.1700

Data Index: 2412949 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7737. Min Act: -0.1700

Data Index: 1514971 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7704. Min Act: -0.1700

Data Index: 8358351 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7737. Min Act: -0.1700

Data Index: 8396183 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7739. Min Act: -0.1700

Data Index: 5264161 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7653. Min Act: -0.1700

Data Index: 6415971 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7713. Min Act: -0.1700

Data Index: 531954 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7438. Min Act: -0.1700

Data Index: 5372469 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7312. Min Act: -0.1700

Data Index: 3160846 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.9243. Min Range: -5.9243

Max Act: 5.7558. Min Act: -0.1700

Data Index: 2937161 (Open Web Text)

Max Activating Token Index: 4