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

Dataset: Open Web Text

Neuron 647 in Layer 1

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: 1.8243. Min Range: -1.8243

Max Act: 1.8243. Min Act: -0.1700

Data Index: 6101626 (Open Web Text)

Max Activating Token Index: 555

Text #1

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7784. Min Act: -0.1700

Data Index: 1840864 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7813. Min Act: -0.1700

Data Index: 6626777 (Open Web Text)

Max Activating Token Index: 113

Text #3

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7690. Min Act: -0.1700

Data Index: 8338903 (Open Web Text)

Max Activating Token Index: 521

Text #4

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7250. Min Act: -0.1700

Data Index: 8338912 (Open Web Text)

Max Activating Token Index: 66

Text #5

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7249. Min Act: -0.1700

Data Index: 151973 (Open Web Text)

Max Activating Token Index: 169

Text #6

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7332. Min Act: -0.1699

Data Index: 4870228 (Open Web Text)

Max Activating Token Index: 87

Text #7

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7177. Min Act: -0.1700

Data Index: 8338904 (Open Web Text)

Max Activating Token Index: 67

Text #8

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7074. Min Act: -0.1700

Data Index: 8537272 (Open Web Text)

Max Activating Token Index: 80

Text #9

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6901. Min Act: -0.1700

Data Index: 2936775 (Open Web Text)

Max Activating Token Index: 207

Text #10

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6823. Min Act: -0.1700

Data Index: 4708295 (Open Web Text)

Max Activating Token Index: 158

Text #11

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6739. Min Act: -0.1700

Data Index: 4613845 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6688. Min Act: -0.1700

Data Index: 7132565 (Open Web Text)

Max Activating Token Index: 756

Text #13

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6737. Min Act: -0.1700

Data Index: 1187023 (Open Web Text)

Max Activating Token Index: 135

Text #14

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6747. Min Act: -0.1700

Data Index: 3662283 (Open Web Text)

Max Activating Token Index: 104

Text #15

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6762. Min Act: -0.1700

Data Index: 8338905 (Open Web Text)

Max Activating Token Index: 606

Text #16

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6573. Min Act: -0.1700

Data Index: 3391618 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6582. Min Act: -0.1700

Data Index: 7674151 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6469. Min Act: -0.1700

Data Index: 4374826 (Open Web Text)

Max Activating Token Index: 895

Text #19

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6561. Min Act: -0.1700

Data Index: 3465683 (Open Web Text)

Max Activating Token Index: 91