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

Dataset: Open Web Text

Neuron 172 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: 2.7809. Min Range: -2.7809

Max Act: 2.7809. Min Act: -0.1700

Data Index: 8029171 (Open Web Text)

Max Activating Token Index: 56

Text #1

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7683. Min Act: -0.1700

Data Index: 5749998 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7665. Min Act: -0.1700

Data Index: 3734300 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7423. Min Act: -0.1700

Data Index: 2818344 (Open Web Text)

Max Activating Token Index: 119

Text #4

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7564. Min Act: -0.1700

Data Index: 499612 (Open Web Text)

Max Activating Token Index: 161

Text #5

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7424. Min Act: -0.1700

Data Index: 8515031 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7268. Min Act: -0.1700

Data Index: 2837838 (Open Web Text)

Max Activating Token Index: 77

Text #7

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7285. Min Act: -0.1700

Data Index: 1321277 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7385. Min Act: -0.1700

Data Index: 2890595 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7298. Min Act: -0.1700

Data Index: 4470979 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7307. Min Act: -0.1700

Data Index: 3117850 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7179. Min Act: -0.1700

Data Index: 1429465 (Open Web Text)

Max Activating Token Index: 55

Text #12

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7116. Min Act: -0.1700

Data Index: 7840032 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7254. Min Act: -0.1700

Data Index: 6943680 (Open Web Text)

Max Activating Token Index: 426

Text #14

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7184. Min Act: -0.1700

Data Index: 6132269 (Open Web Text)

Max Activating Token Index: 40

Text #15

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7229. Min Act: -0.1700

Data Index: 4581260 (Open Web Text)

Max Activating Token Index: 70

Text #16

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7085. Min Act: -0.1700

Data Index: 6594785 (Open Web Text)

Max Activating Token Index: 364

Text #17

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7036. Min Act: -0.1700

Data Index: 2946871 (Open Web Text)

Max Activating Token Index: 36

Text #18

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.7049. Min Act: -0.1700

Data Index: 1667258 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 2.7809. Min Range: -2.7809

Max Act: 2.6878. Min Act: -0.1700

Data Index: 2046197 (Open Web Text)

Max Activating Token Index: 718