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

Dataset: Open Web Text

Neuron 667 in Layer 5

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: 3.1091. Min Range: -3.1091

Max Act: 3.1091. Min Act: -0.1700

Data Index: 5236322 (Open Web Text)

Max Activating Token Index: 904

Text #1

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0470. Min Act: -0.1700

Data Index: 5865028 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0027. Min Act: -0.1700

Data Index: 573032 (Open Web Text)

Max Activating Token Index: 475

Text #3

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0310. Min Act: -0.1700

Data Index: 1217899 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0102. Min Act: -0.1700

Data Index: 8677522 (Open Web Text)

Max Activating Token Index: 672

Text #5

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0175. Min Act: -0.1700

Data Index: 8649200 (Open Web Text)

Max Activating Token Index: 988

Text #6

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0345. Min Act: -0.1700

Data Index: 7644355 (Open Web Text)

Max Activating Token Index: 959

Text #7

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0267. Min Act: -0.1700

Data Index: 6169470 (Open Web Text)

Max Activating Token Index: 243

Text #8

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0138. Min Act: -0.1700

Data Index: 531814 (Open Web Text)

Max Activating Token Index: 578

Text #9

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0134. Min Act: -0.1700

Data Index: 3738800 (Open Web Text)

Max Activating Token Index: 811

Text #10

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.9925. Min Act: -0.1700

Data Index: 2488021 (Open Web Text)

Max Activating Token Index: 525

Text #11

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0019. Min Act: -0.1700

Data Index: 7416615 (Open Web Text)

Max Activating Token Index: 807

Text #12

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.9903. Min Act: -0.1700

Data Index: 11727 (Open Web Text)

Max Activating Token Index: 961

Text #13

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0130. Min Act: -0.1700

Data Index: 947188 (Open Web Text)

Max Activating Token Index: 801

Text #14

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.0160. Min Act: -0.1700

Data Index: 5344070 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.9662. Min Act: -0.1700

Data Index: 7260627 (Open Web Text)

Max Activating Token Index: 270

Text #16

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.9882. Min Act: -0.1700

Data Index: 3911049 (Open Web Text)

Max Activating Token Index: 902

Text #17

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.9761. Min Act: -0.1700

Data Index: 1136353 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.9572. Min Act: -0.1700

Data Index: 7100183 (Open Web Text)

Max Activating Token Index: 544

Text #19

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.9528. Min Act: -0.1700

Data Index: 2111062 (Open Web Text)

Max Activating Token Index: 522