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

Dataset: Open Web Text

Neuron 2669 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: 1.7873. Min Range: -1.7873

Max Act: 1.7873. Min Act: -0.1700

Data Index: 2977871 (Open Web Text)

Max Activating Token Index: 54

Text #1

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7587. Min Act: -0.1700

Data Index: 1253036 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7425. Min Act: -0.1700

Data Index: 5191094 (Open Web Text)

Max Activating Token Index: 52

Text #3

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7333. Min Act: -0.1700

Data Index: 915011 (Open Web Text)

Max Activating Token Index: 28

Text #4

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7278. Min Act: -0.1700

Data Index: 2835625 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7226. Min Act: -0.1700

Data Index: 7807412 (Open Web Text)

Max Activating Token Index: 31

Text #6

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7066. Min Act: -0.1700

Data Index: 7612707 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7137. Min Act: -0.1700

Data Index: 51604 (Open Web Text)

Max Activating Token Index: 402

Text #8

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7039. Min Act: -0.1700

Data Index: 7611978 (Open Web Text)

Max Activating Token Index: 101

Text #9

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6937. Min Act: -0.1700

Data Index: 617798 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6930. Min Act: -0.1700

Data Index: 7538197 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6987. Min Act: -0.1700

Data Index: 5551811 (Open Web Text)

Max Activating Token Index: 139

Text #12

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6958. Min Act: -0.1700

Data Index: 4234574 (Open Web Text)

Max Activating Token Index: 590

Text #13

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6907. Min Act: -0.1700

Data Index: 873302 (Open Web Text)

Max Activating Token Index: 855

Text #14

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6761. Min Act: -0.1700

Data Index: 5804409 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6735. Min Act: -0.1700

Data Index: 3083346 (Open Web Text)

Max Activating Token Index: 163

Text #16

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6812. Min Act: -0.1700

Data Index: 1112728 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6682. Min Act: -0.1700

Data Index: 2728791 (Open Web Text)

Max Activating Token Index: 48

Text #18

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6589. Min Act: -0.1700

Data Index: 1372247 (Open Web Text)

Max Activating Token Index: 101

Text #19

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.6708. Min Act: -0.1700

Data Index: 7963041 (Open Web Text)

Max Activating Token Index: 581