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

Dataset: Open Web Text

Neuron 1207 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: 5.6764. Min Range: -5.6764

Max Act: 5.6747. Min Act: -0.1700

Data Index: 2248182 (Open Web Text)

Max Activating Token Index: 612

Text #1

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.6764. Min Act: -0.1700

Data Index: 6108292 (Open Web Text)

Max Activating Token Index: 806

Text #2

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.6063. Min Act: -0.1700

Data Index: 8405141 (Open Web Text)

Max Activating Token Index: 860

Text #3

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5966. Min Act: -0.1700

Data Index: 1009576 (Open Web Text)

Max Activating Token Index: 627

Text #4

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5749. Min Act: -0.1700

Data Index: 2979189 (Open Web Text)

Max Activating Token Index: 475

Text #5

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5225. Min Act: -0.1700

Data Index: 3672250 (Open Web Text)

Max Activating Token Index: 201

Text #6

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5290. Min Act: -0.1700

Data Index: 1526143 (Open Web Text)

Max Activating Token Index: 590

Text #7

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5330. Min Act: -0.1700

Data Index: 7730025 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5206. Min Act: -0.1700

Data Index: 8213749 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5107. Min Act: -0.1700

Data Index: 7015466 (Open Web Text)

Max Activating Token Index: 98

Text #10

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5136. Min Act: -0.1700

Data Index: 4241314 (Open Web Text)

Max Activating Token Index: 311

Text #11

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5142. Min Act: -0.1700

Data Index: 6468959 (Open Web Text)

Max Activating Token Index: 535

Text #12

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5014. Min Act: -0.1700

Data Index: 2003865 (Open Web Text)

Max Activating Token Index: 579

Text #13

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.4725. Min Act: -0.1700

Data Index: 4703421 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.4737. Min Act: -0.1700

Data Index: 4053143 (Open Web Text)

Max Activating Token Index: 396

Text #15

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.4771. Min Act: -0.1700

Data Index: 2459560 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.4882. Min Act: -0.1700

Data Index: 6309259 (Open Web Text)

Max Activating Token Index: 722

Text #17

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.4304. Min Act: -0.1700

Data Index: 1106433 (Open Web Text)

Max Activating Token Index: 183

Text #18

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.5038. Min Act: -0.1700

Data Index: 4124998 (Open Web Text)

Max Activating Token Index: 983

Text #19

Max Range: 5.6764. Min Range: -5.6764

Max Act: 5.4392. Min Act: -0.1700

Data Index: 6167325 (Open Web Text)

Max Activating Token Index: 742