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

Dataset: Open Web Text

Neuron 1667 in Layer 2

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: 4.2952. Min Range: -4.2952

Max Act: 4.2952. Min Act: -0.1700

Data Index: 5825427 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.2952. Min Range: -4.2952

Max Act: 4.2768. Min Act: -0.1700

Data Index: 5359782 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 4.2952. Min Range: -4.2952

Max Act: 4.1144. Min Act: -0.1700

Data Index: 8416953 (Open Web Text)

Max Activating Token Index: 47

Text #3

Max Range: 4.2952. Min Range: -4.2952

Max Act: 4.0628. Min Act: -0.1700

Data Index: 452722 (Open Web Text)

Max Activating Token Index: 41

Text #4

Max Range: 4.2952. Min Range: -4.2952

Max Act: 4.0228. Min Act: -0.1700

Data Index: 5202211 (Open Web Text)

Max Activating Token Index: 888

Text #5

Max Range: 4.2952. Min Range: -4.2952

Max Act: 4.0238. Min Act: -0.1700

Data Index: 1693500 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 4.2952. Min Range: -4.2952

Max Act: 4.0146. Min Act: -0.1700

Data Index: 8086545 (Open Web Text)

Max Activating Token Index: 37

Text #7

Max Range: 4.2952. Min Range: -4.2952

Max Act: 4.0190. Min Act: -0.1700

Data Index: 5500910 (Open Web Text)

Max Activating Token Index: 309

Text #8

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9860. Min Act: -0.1700

Data Index: 2065965 (Open Web Text)

Max Activating Token Index: 268

Text #9

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9751. Min Act: -0.1700

Data Index: 3012058 (Open Web Text)

Max Activating Token Index: 118

Text #10

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9675. Min Act: -0.1700

Data Index: 3851371 (Open Web Text)

Max Activating Token Index: 48

Text #11

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9325. Min Act: -0.1700

Data Index: 7320833 (Open Web Text)

Max Activating Token Index: 54

Text #12

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9606. Min Act: -0.1700

Data Index: 3898078 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9507. Min Act: -0.1700

Data Index: 8006921 (Open Web Text)

Max Activating Token Index: 29

Text #14

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9185. Min Act: -0.1700

Data Index: 5993138 (Open Web Text)

Max Activating Token Index: 1007

Text #15

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9440. Min Act: -0.1700

Data Index: 609324 (Open Web Text)

Max Activating Token Index: 602

Text #16

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9556. Min Act: -0.1700

Data Index: 8238061 (Open Web Text)

Max Activating Token Index: 669

Text #17

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9365. Min Act: -0.1700

Data Index: 2803006 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9296. Min Act: -0.1700

Data Index: 7266858 (Open Web Text)

Max Activating Token Index: 111

Text #19

Max Range: 4.2952. Min Range: -4.2952

Max Act: 3.9439. Min Act: -0.1700

Data Index: 5269546 (Open Web Text)

Max Activating Token Index: 543