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

Dataset: Open Web Text

Neuron 1292 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: 4.3952. Min Range: -4.3952

Max Act: 4.3952. Min Act: -0.1700

Data Index: 8010427 (Open Web Text)

Max Activating Token Index: 199

Text #1

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.3457. Min Act: -0.1700

Data Index: 2555427 (Open Web Text)

Max Activating Token Index: 93

Text #2

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.3239. Min Act: -0.1700

Data Index: 5398061 (Open Web Text)

Max Activating Token Index: 911

Text #3

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.2358. Min Act: -0.1700

Data Index: 5948225 (Open Web Text)

Max Activating Token Index: 69

Text #4

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.2942. Min Act: -0.1700

Data Index: 6529924 (Open Web Text)

Max Activating Token Index: 121

Text #5

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.2041. Min Act: -0.1700

Data Index: 6221727 (Open Web Text)

Max Activating Token Index: 100

Text #6

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.2307. Min Act: -0.1700

Data Index: 2641319 (Open Web Text)

Max Activating Token Index: 96

Text #7

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.2510. Min Act: -0.1700

Data Index: 7022224 (Open Web Text)

Max Activating Token Index: 88

Text #8

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.2626. Min Act: -0.1700

Data Index: 3981435 (Open Web Text)

Max Activating Token Index: 882

Text #9

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.1882. Min Act: -0.1700

Data Index: 2877007 (Open Web Text)

Max Activating Token Index: 170

Text #10

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.1584. Min Act: -0.1700

Data Index: 4746655 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.1675. Min Act: -0.1700

Data Index: 5649577 (Open Web Text)

Max Activating Token Index: 225

Text #12

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.2017. Min Act: -0.1700

Data Index: 3743385 (Open Web Text)

Max Activating Token Index: 394

Text #13

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.1978. Min Act: -0.1700

Data Index: 6139285 (Open Web Text)

Max Activating Token Index: 47

Text #14

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.1787. Min Act: -0.1700

Data Index: 1734823 (Open Web Text)

Max Activating Token Index: 176

Text #15

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.1839. Min Act: -0.1700

Data Index: 3582554 (Open Web Text)

Max Activating Token Index: 127

Text #16

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.1726. Min Act: -0.1700

Data Index: 402781 (Open Web Text)

Max Activating Token Index: 1000

Text #17

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.1565. Min Act: -0.1700

Data Index: 598772 (Open Web Text)

Max Activating Token Index: 187

Text #18

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.1697. Min Act: -0.1700

Data Index: 332916 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 4.3952. Min Range: -4.3952

Max Act: 4.1440. Min Act: -0.1700

Data Index: 6030822 (Open Web Text)

Max Activating Token Index: 147