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

Dataset: Open Web Text

Neuron 851 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: 1.7283. Min Range: -1.7283

Max Act: 1.7283. Min Act: -0.1700

Data Index: 7692346 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.6580. Min Act: -0.1699

Data Index: 5530919 (Open Web Text)

Max Activating Token Index: 302

Text #2

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5862. Min Act: -0.1700

Data Index: 6825648 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5780. Min Act: -0.1700

Data Index: 3805400 (Open Web Text)

Max Activating Token Index: 269

Text #4

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5623. Min Act: -0.1700

Data Index: 6486245 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5545. Min Act: -0.1700

Data Index: 5818223 (Open Web Text)

Max Activating Token Index: 86

Text #6

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5552. Min Act: -0.1700

Data Index: 1411930 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5507. Min Act: -0.1700

Data Index: 20116 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5449. Min Act: -0.1700

Data Index: 8514393 (Open Web Text)

Max Activating Token Index: 388

Text #9

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5416. Min Act: -0.1700

Data Index: 8530477 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5257. Min Act: -0.1700

Data Index: 1545331 (Open Web Text)

Max Activating Token Index: 621

Text #11

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5101. Min Act: -0.1700

Data Index: 7527896 (Open Web Text)

Max Activating Token Index: 254

Text #12

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5149. Min Act: -0.1700

Data Index: 4461757 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5112. Min Act: -0.1700

Data Index: 1378112 (Open Web Text)

Max Activating Token Index: 67

Text #14

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4994. Min Act: -0.1700

Data Index: 5445352 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4980. Min Act: -0.1700

Data Index: 7239922 (Open Web Text)

Max Activating Token Index: 1014

Text #16

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5020. Min Act: -0.1700

Data Index: 4092256 (Open Web Text)

Max Activating Token Index: 858

Text #17

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4858. Min Act: -0.1700

Data Index: 6442700 (Open Web Text)

Max Activating Token Index: 829

Text #18

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5018. Min Act: -0.1700

Data Index: 4938583 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4805. Min Act: -0.1700

Data Index: 5975288 (Open Web Text)

Max Activating Token Index: 7