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

Dataset: Open Web Text

Neuron 1470 in Layer 2

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: 2.4345. Min Range: -2.4345

Max Act: 2.4201. Min Act: -0.1700

Data Index: 8710396 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.4125. Min Act: -0.1700

Data Index: 1476044 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.4345. Min Act: -0.1700

Data Index: 4198378 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.4054. Min Act: -0.1700

Data Index: 3516890 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.3455. Min Act: -0.1700

Data Index: 8699822 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.3269. Min Act: -0.1700

Data Index: 3758254 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.3364. Min Act: -0.1700

Data Index: 751709 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.3178. Min Act: -0.1700

Data Index: 299009 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.2641. Min Act: -0.1700

Data Index: 2737610 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.2615. Min Act: -0.1700

Data Index: 3983983 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.2653. Min Act: -0.1700

Data Index: 7513513 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.2810. Min Act: -0.1700

Data Index: 39845 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.2400. Min Act: -0.1700

Data Index: 3603960 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.2253. Min Act: -0.1700

Data Index: 3177326 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.2249. Min Act: -0.1700

Data Index: 3020679 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.2413. Min Act: -0.1700

Data Index: 836110 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.2055. Min Act: -0.1700

Data Index: 300528 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.2369. Min Act: -0.1700

Data Index: 4237257 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.1974. Min Act: -0.1700

Data Index: 6959635 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.4345. Min Range: -2.4345

Max Act: 2.1987. Min Act: -0.1700

Data Index: 6738480 (Open Web Text)

Max Activating Token Index: 1023