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

Dataset: Open Web Text

Neuron 3037 in Layer 4

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: 4.4675. Min Range: -4.4675

Max Act: 4.4581. Min Act: -0.1700

Data Index: 1582828 (Open Web Text)

Max Activating Token Index: 407

Text #1

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4675. Min Act: -0.1700

Data Index: 6006521 (Open Web Text)

Max Activating Token Index: 536

Text #2

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4505. Min Act: -0.1700

Data Index: 3947307 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4246. Min Act: -0.1700

Data Index: 5372851 (Open Web Text)

Max Activating Token Index: 553

Text #4

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4165. Min Act: -0.1700

Data Index: 6177315 (Open Web Text)

Max Activating Token Index: 495

Text #5

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4331. Min Act: -0.1700

Data Index: 4117095 (Open Web Text)

Max Activating Token Index: 385

Text #6

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4553. Min Act: -0.1700

Data Index: 1466678 (Open Web Text)

Max Activating Token Index: 1002

Text #7

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4204. Min Act: -0.1700

Data Index: 6473859 (Open Web Text)

Max Activating Token Index: 399

Text #8

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4133. Min Act: -0.1700

Data Index: 8199802 (Open Web Text)

Max Activating Token Index: 635

Text #9

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4183. Min Act: -0.1700

Data Index: 1334408 (Open Web Text)

Max Activating Token Index: 925

Text #10

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4114. Min Act: -0.1700

Data Index: 2204342 (Open Web Text)

Max Activating Token Index: 508

Text #11

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3874. Min Act: -0.1700

Data Index: 7847131 (Open Web Text)

Max Activating Token Index: 393

Text #12

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3854. Min Act: -0.1700

Data Index: 7783028 (Open Web Text)

Max Activating Token Index: 132

Text #13

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3910. Min Act: -0.1700

Data Index: 1252051 (Open Web Text)

Max Activating Token Index: 47

Text #14

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3807. Min Act: -0.1700

Data Index: 542875 (Open Web Text)

Max Activating Token Index: 274

Text #15

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4182. Min Act: -0.1700

Data Index: 3428964 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3951. Min Act: -0.1700

Data Index: 1993470 (Open Web Text)

Max Activating Token Index: 778

Text #17

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.4129. Min Act: -0.1700

Data Index: 7001891 (Open Web Text)

Max Activating Token Index: 244

Text #18

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3812. Min Act: -0.1700

Data Index: 4636225 (Open Web Text)

Max Activating Token Index: 608

Text #19

Max Range: 4.4675. Min Range: -4.4675

Max Act: 4.3943. Min Act: -0.1700

Data Index: 2486823 (Open Web Text)

Max Activating Token Index: 926