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

Dataset: Open Web Text

Neuron 2259 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: 5.9577. Min Range: -5.9577

Max Act: 5.9568. Min Act: -0.1700

Data Index: 2106930 (Open Web Text)

Max Activating Token Index: 663

Text #1

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.9577. Min Act: -0.1700

Data Index: 3960134 (Open Web Text)

Max Activating Token Index: 645

Text #2

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.9489. Min Act: -0.1700

Data Index: 3993444 (Open Web Text)

Max Activating Token Index: 219

Text #3

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.9421. Min Act: -0.1700

Data Index: 8794135 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8998. Min Act: -0.1700

Data Index: 4337176 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.9241. Min Act: -0.1700

Data Index: 3064378 (Open Web Text)

Max Activating Token Index: 64

Text #6

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8967. Min Act: -0.1700

Data Index: 5581754 (Open Web Text)

Max Activating Token Index: 35

Text #7

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8890. Min Act: -0.1700

Data Index: 6726194 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8976. Min Act: -0.1700

Data Index: 1349178 (Open Web Text)

Max Activating Token Index: 185

Text #9

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8856. Min Act: -0.1700

Data Index: 1088255 (Open Web Text)

Max Activating Token Index: 621

Text #10

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8778. Min Act: -0.1700

Data Index: 754241 (Open Web Text)

Max Activating Token Index: 461

Text #11

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8678. Min Act: -0.1700

Data Index: 8353339 (Open Web Text)

Max Activating Token Index: 34

Text #12

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8692. Min Act: -0.1700

Data Index: 7733519 (Open Web Text)

Max Activating Token Index: 186

Text #13

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8901. Min Act: -0.1700

Data Index: 2537347 (Open Web Text)

Max Activating Token Index: 124

Text #14

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8706. Min Act: -0.1700

Data Index: 2386617 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8684. Min Act: -0.1700

Data Index: 6418228 (Open Web Text)

Max Activating Token Index: 78

Text #16

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8775. Min Act: -0.1700

Data Index: 5886889 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8681. Min Act: -0.1700

Data Index: 2108648 (Open Web Text)

Max Activating Token Index: 367

Text #18

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8482. Min Act: -0.1700

Data Index: 5405396 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 5.9577. Min Range: -5.9577

Max Act: 5.8443. Min Act: -0.1700

Data Index: 5470223 (Open Web Text)

Max Activating Token Index: 6