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

Dataset: Open Web Text

Neuron 335 in Layer 3

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: 3.8172. Min Range: -3.8172

Max Act: 3.8172. Min Act: -0.1700

Data Index: 6133619 (Open Web Text)

Max Activating Token Index: 838

Text #1

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6768. Min Act: -0.1700

Data Index: 4059549 (Open Web Text)

Max Activating Token Index: 793

Text #2

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.7003. Min Act: -0.1700

Data Index: 3800879 (Open Web Text)

Max Activating Token Index: 819

Text #3

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6694. Min Act: -0.1700

Data Index: 5073090 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6281. Min Act: -0.1700

Data Index: 4118928 (Open Web Text)

Max Activating Token Index: 465

Text #5

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6672. Min Act: -0.1700

Data Index: 4764089 (Open Web Text)

Max Activating Token Index: 473

Text #6

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6718. Min Act: -0.1700

Data Index: 8059263 (Open Web Text)

Max Activating Token Index: 530

Text #7

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6458. Min Act: -0.1700

Data Index: 4874750 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.7237. Min Act: -0.1700

Data Index: 1518300 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6293. Min Act: -0.1700

Data Index: 1598432 (Open Web Text)

Max Activating Token Index: 224

Text #10

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6751. Min Act: -0.1700

Data Index: 6582225 (Open Web Text)

Max Activating Token Index: 667

Text #11

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6867. Min Act: -0.1700

Data Index: 5793081 (Open Web Text)

Max Activating Token Index: 171

Text #12

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6433. Min Act: -0.1700

Data Index: 6743152 (Open Web Text)

Max Activating Token Index: 640

Text #13

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6517. Min Act: -0.1700

Data Index: 1924164 (Open Web Text)

Max Activating Token Index: 465

Text #14

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6610. Min Act: -0.1700

Data Index: 3690959 (Open Web Text)

Max Activating Token Index: 23

Text #15

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6510. Min Act: -0.1700

Data Index: 3646800 (Open Web Text)

Max Activating Token Index: 299

Text #16

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6052. Min Act: -0.1700

Data Index: 3309190 (Open Web Text)

Max Activating Token Index: 952

Text #17

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6193. Min Act: -0.1700

Data Index: 4941077 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6059. Min Act: -0.1700

Data Index: 2905580 (Open Web Text)

Max Activating Token Index: 954

Text #19

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.5904. Min Act: -0.1700

Data Index: 2812128 (Open Web Text)

Max Activating Token Index: 492