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

Dataset: Open Web Text

Neuron 1741 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: 3.2993. Min Range: -3.2993

Max Act: 3.2993. Min Act: -0.1700

Data Index: 7310873 (Open Web Text)

Max Activating Token Index: 701

Text #1

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.2065. Min Act: -0.1700

Data Index: 4595166 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.1746. Min Act: -0.1700

Data Index: 8787666 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.1856. Min Act: -0.1700

Data Index: 6639781 (Open Web Text)

Max Activating Token Index: 221

Text #4

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.1415. Min Act: -0.1700

Data Index: 6685199 (Open Web Text)

Max Activating Token Index: 88

Text #5

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1350126 (Open Web Text)

Max Activating Token Index: 308

Text #6

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0819. Min Act: -0.1700

Data Index: 8437542 (Open Web Text)

Max Activating Token Index: 142

Text #7

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0720. Min Act: -0.1700

Data Index: 2435266 (Open Web Text)

Max Activating Token Index: 165

Text #8

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0497. Min Act: -0.1700

Data Index: 2106774 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0731. Min Act: -0.1700

Data Index: 3060378 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0571. Min Act: -0.1700

Data Index: 3035261 (Open Web Text)

Max Activating Token Index: 561

Text #11

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0644. Min Act: -0.1700

Data Index: 5018478 (Open Web Text)

Max Activating Token Index: 221

Text #12

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0659. Min Act: -0.1700

Data Index: 8205726 (Open Web Text)

Max Activating Token Index: 737

Text #13

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0797. Min Act: -0.1700

Data Index: 6509109 (Open Web Text)

Max Activating Token Index: 986

Text #14

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0673. Min Act: -0.1700

Data Index: 2295336 (Open Web Text)

Max Activating Token Index: 182

Text #15

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0565. Min Act: -0.1700

Data Index: 1907550 (Open Web Text)

Max Activating Token Index: 213

Text #16

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0827. Min Act: -0.1700

Data Index: 1530127 (Open Web Text)

Max Activating Token Index: 281

Text #17

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0384. Min Act: -0.1700

Data Index: 7624273 (Open Web Text)

Max Activating Token Index: 395

Text #18

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0465. Min Act: -0.1700

Data Index: 7698145 (Open Web Text)

Max Activating Token Index: 174

Text #19

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.0576. Min Act: -0.1700

Data Index: 7746648 (Open Web Text)

Max Activating Token Index: 53