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

Dataset: Open Web Text

Neuron 1667 in Layer 5

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: 4.5062. Min Range: -4.5062

Max Act: 4.5062. Min Act: -0.1700

Data Index: 1109 (Open Web Text)

Max Activating Token Index: 31

Text #1

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.3543. Min Act: -0.1700

Data Index: 5878777 (Open Web Text)

Max Activating Token Index: 358

Text #2

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.3416. Min Act: -0.1700

Data Index: 7317469 (Open Web Text)

Max Activating Token Index: 677

Text #3

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.3168. Min Act: -0.1700

Data Index: 1876784 (Open Web Text)

Max Activating Token Index: 984

Text #4

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2836. Min Act: -0.1700

Data Index: 4820029 (Open Web Text)

Max Activating Token Index: 1014

Text #5

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2684. Min Act: -0.1700

Data Index: 1297781 (Open Web Text)

Max Activating Token Index: 799

Text #6

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2826. Min Act: -0.1700

Data Index: 6483098 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2757. Min Act: -0.1700

Data Index: 876103 (Open Web Text)

Max Activating Token Index: 574

Text #8

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2213. Min Act: -0.1700

Data Index: 7696336 (Open Web Text)

Max Activating Token Index: 284

Text #9

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2405. Min Act: -0.1700

Data Index: 4809521 (Open Web Text)

Max Activating Token Index: 866

Text #10

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2171. Min Act: -0.1700

Data Index: 4623448 (Open Web Text)

Max Activating Token Index: 710

Text #11

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2326. Min Act: -0.1700

Data Index: 7261964 (Open Web Text)

Max Activating Token Index: 925

Text #12

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2603. Min Act: -0.1700

Data Index: 1752896 (Open Web Text)

Max Activating Token Index: 372

Text #13

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.1780. Min Act: -0.1700

Data Index: 287259 (Open Web Text)

Max Activating Token Index: 146

Text #14

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2284. Min Act: -0.1700

Data Index: 3482093 (Open Web Text)

Max Activating Token Index: 929

Text #15

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2114. Min Act: -0.1700

Data Index: 8519063 (Open Web Text)

Max Activating Token Index: 464

Text #16

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.1943. Min Act: -0.1700

Data Index: 230372 (Open Web Text)

Max Activating Token Index: 430

Text #17

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2120. Min Act: -0.1700

Data Index: 104256 (Open Web Text)

Max Activating Token Index: 540

Text #18

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.2142. Min Act: -0.1700

Data Index: 4501281 (Open Web Text)

Max Activating Token Index: 30

Text #19

Max Range: 4.5062. Min Range: -4.5062

Max Act: 4.1500. Min Act: -0.1700

Data Index: 3145214 (Open Web Text)

Max Activating Token Index: 786