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

Dataset: Open Web Text

Neuron 931 in Layer 1

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: 3.7922. Min Range: -3.7922

Max Act: 3.7922. Min Act: -0.1700

Data Index: 4447432 (Open Web Text)

Max Activating Token Index: 120

Text #1

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7759. Min Act: -0.1700

Data Index: 3956982 (Open Web Text)

Max Activating Token Index: 607

Text #2

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7656. Min Act: -0.1700

Data Index: 727013 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7825. Min Act: -0.1700

Data Index: 2109809 (Open Web Text)

Max Activating Token Index: 713

Text #4

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7564. Min Act: -0.1700

Data Index: 5052127 (Open Web Text)

Max Activating Token Index: 576

Text #5

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7343. Min Act: -0.1700

Data Index: 201886 (Open Web Text)

Max Activating Token Index: 811

Text #6

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7319. Min Act: -0.1700

Data Index: 3634337 (Open Web Text)

Max Activating Token Index: 271

Text #7

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7324. Min Act: -0.1700

Data Index: 965252 (Open Web Text)

Max Activating Token Index: 648

Text #8

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7312. Min Act: -0.1700

Data Index: 4060311 (Open Web Text)

Max Activating Token Index: 444

Text #9

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7304. Min Act: -0.1700

Data Index: 7135130 (Open Web Text)

Max Activating Token Index: 652

Text #10

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7048. Min Act: -0.1700

Data Index: 2624446 (Open Web Text)

Max Activating Token Index: 102

Text #11

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7270. Min Act: -0.1700

Data Index: 7864109 (Open Web Text)

Max Activating Token Index: 162

Text #12

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7042. Min Act: -0.1700

Data Index: 8087911 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7016. Min Act: -0.1700

Data Index: 4331599 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6901. Min Act: -0.1700

Data Index: 3440995 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7101. Min Act: -0.1700

Data Index: 2323165 (Open Web Text)

Max Activating Token Index: 294

Text #16

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.7186. Min Act: -0.1700

Data Index: 6214204 (Open Web Text)

Max Activating Token Index: 534

Text #17

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6857. Min Act: -0.1700

Data Index: 2844470 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6598. Min Act: -0.1700

Data Index: 6064427 (Open Web Text)

Max Activating Token Index: 385

Text #19

Max Range: 3.7922. Min Range: -3.7922

Max Act: 3.6699. Min Act: -0.1700

Data Index: 6473420 (Open Web Text)

Max Activating Token Index: 447