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

Dataset: Open Web Text

Neuron 767 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: 4.1592. Min Range: -4.1592

Max Act: 4.1592. Min Act: -0.1700

Data Index: 3888646 (Open Web Text)

Max Activating Token Index: 289

Text #1

Max Range: 4.1592. Min Range: -4.1592

Max Act: 4.0712. Min Act: -0.1700

Data Index: 6553383 (Open Web Text)

Max Activating Token Index: 271

Text #2

Max Range: 4.1592. Min Range: -4.1592

Max Act: 4.0966. Min Act: -0.1700

Data Index: 4823852 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 4.1592. Min Range: -4.1592

Max Act: 4.0551. Min Act: -0.1700

Data Index: 5578897 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 4.1592. Min Range: -4.1592

Max Act: 4.0706. Min Act: -0.1700

Data Index: 3888644 (Open Web Text)

Max Activating Token Index: 96

Text #5

Max Range: 4.1592. Min Range: -4.1592

Max Act: 4.0603. Min Act: -0.1700

Data Index: 4823848 (Open Web Text)

Max Activating Token Index: 153

Text #6

Max Range: 4.1592. Min Range: -4.1592

Max Act: 4.0501. Min Act: -0.1700

Data Index: 6553382 (Open Web Text)

Max Activating Token Index: 135

Text #7

Max Range: 4.1592. Min Range: -4.1592

Max Act: 4.0192. Min Act: -0.1700

Data Index: 6342028 (Open Web Text)

Max Activating Token Index: 152

Text #8

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.9905. Min Act: -0.1700

Data Index: 6553381 (Open Web Text)

Max Activating Token Index: 401

Text #9

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.9564. Min Act: -0.1700

Data Index: 4343239 (Open Web Text)

Max Activating Token Index: 195

Text #10

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.9750. Min Act: -0.1700

Data Index: 3888649 (Open Web Text)

Max Activating Token Index: 185

Text #11

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.9595. Min Act: -0.1700

Data Index: 6553384 (Open Web Text)

Max Activating Token Index: 609

Text #12

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.9174. Min Act: -0.1700

Data Index: 386281 (Open Web Text)

Max Activating Token Index: 62

Text #13

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.8846. Min Act: -0.1700

Data Index: 4595238 (Open Web Text)

Max Activating Token Index: 798

Text #14

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.9213. Min Act: -0.1700

Data Index: 6553385 (Open Web Text)

Max Activating Token Index: 786

Text #15

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.9278. Min Act: -0.1700

Data Index: 1395562 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.8842. Min Act: -0.1700

Data Index: 6342029 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.8738. Min Act: -0.1700

Data Index: 5785397 (Open Web Text)

Max Activating Token Index: 106

Text #18

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.8437. Min Act: -0.1700

Data Index: 6302062 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 4.1592. Min Range: -4.1592

Max Act: 3.8137. Min Act: -0.1700

Data Index: 4788374 (Open Web Text)

Max Activating Token Index: 424