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

Dataset: Open Web Text

Neuron 1077 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: 4.4237. Min Range: -4.4237

Max Act: 4.4237. Min Act: -0.1700

Data Index: 2190390 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.4228. Min Act: -0.1700

Data Index: 4211120 (Open Web Text)

Max Activating Token Index: 920

Text #2

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.3181. Min Act: -0.1700

Data Index: 6642056 (Open Web Text)

Max Activating Token Index: 920

Text #3

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2712. Min Act: -0.1700

Data Index: 4211108 (Open Web Text)

Max Activating Token Index: 661

Text #4

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2612. Min Act: -0.1700

Data Index: 7437336 (Open Web Text)

Max Activating Token Index: 192

Text #5

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2666. Min Act: -0.1700

Data Index: 6244240 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2391. Min Act: -0.1700

Data Index: 4915761 (Open Web Text)

Max Activating Token Index: 957

Text #7

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2279. Min Act: -0.1700

Data Index: 7469867 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2357. Min Act: -0.1700

Data Index: 6617089 (Open Web Text)

Max Activating Token Index: 1018

Text #9

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2283. Min Act: -0.1700

Data Index: 3759122 (Open Web Text)

Max Activating Token Index: 1013

Text #10

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2145. Min Act: -0.1700

Data Index: 3589050 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2459. Min Act: -0.1700

Data Index: 5087165 (Open Web Text)

Max Activating Token Index: 1008

Text #12

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2527. Min Act: -0.1700

Data Index: 2999985 (Open Web Text)

Max Activating Token Index: 407

Text #13

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2375. Min Act: -0.1700

Data Index: 1972150 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2416. Min Act: -0.1700

Data Index: 4749489 (Open Web Text)

Max Activating Token Index: 912

Text #15

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2558. Min Act: -0.1700

Data Index: 4603796 (Open Web Text)

Max Activating Token Index: 987

Text #16

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2341. Min Act: -0.1700

Data Index: 890412 (Open Web Text)

Max Activating Token Index: 396

Text #17

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2417. Min Act: -0.1700

Data Index: 886266 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2448. Min Act: -0.1700

Data Index: 4474423 (Open Web Text)

Max Activating Token Index: 1003

Text #19

Max Range: 4.4237. Min Range: -4.4237

Max Act: 4.2421. Min Act: -0.1700

Data Index: 1976675 (Open Web Text)

Max Activating Token Index: 366