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

Dataset: Open Web Text

Neuron 2054 in Layer 6

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: 3.8181. Min Range: -3.8181

Max Act: 3.7901. Min Act: -0.1700

Data Index: 5905879 (Open Web Text)

Max Activating Token Index: 546

Text #1

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.8181. Min Act: -0.1700

Data Index: 5064375 (Open Web Text)

Max Activating Token Index: 792

Text #2

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.7041. Min Act: -0.1700

Data Index: 5727926 (Open Web Text)

Max Activating Token Index: 476

Text #3

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.6867. Min Act: -0.1700

Data Index: 3170857 (Open Web Text)

Max Activating Token Index: 826

Text #4

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.7113. Min Act: -0.1700

Data Index: 4149680 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.6515. Min Act: -0.1700

Data Index: 707618 (Open Web Text)

Max Activating Token Index: 808

Text #6

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.6505. Min Act: -0.1700

Data Index: 7547105 (Open Web Text)

Max Activating Token Index: 407

Text #7

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5977. Min Act: -0.1700

Data Index: 3387180 (Open Web Text)

Max Activating Token Index: 948

Text #8

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5846. Min Act: -0.1700

Data Index: 4409310 (Open Web Text)

Max Activating Token Index: 725

Text #9

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5894. Min Act: -0.1700

Data Index: 1531931 (Open Web Text)

Max Activating Token Index: 621

Text #10

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5924. Min Act: -0.1700

Data Index: 60777 (Open Web Text)

Max Activating Token Index: 737

Text #11

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5960. Min Act: -0.1700

Data Index: 574033 (Open Web Text)

Max Activating Token Index: 109

Text #12

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5816. Min Act: -0.1700

Data Index: 4102705 (Open Web Text)

Max Activating Token Index: 175

Text #13

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5813. Min Act: -0.1700

Data Index: 4578145 (Open Web Text)

Max Activating Token Index: 560

Text #14

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5569. Min Act: -0.1700

Data Index: 1789901 (Open Web Text)

Max Activating Token Index: 455

Text #15

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5711. Min Act: -0.1700

Data Index: 3998292 (Open Web Text)

Max Activating Token Index: 868

Text #16

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5887. Min Act: -0.1700

Data Index: 7432671 (Open Web Text)

Max Activating Token Index: 901

Text #17

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5475. Min Act: -0.1700

Data Index: 4758604 (Open Web Text)

Max Activating Token Index: 193

Text #18

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5301. Min Act: -0.1700

Data Index: 2079631 (Open Web Text)

Max Activating Token Index: 539

Text #19

Max Range: 3.8181. Min Range: -3.8181

Max Act: 3.5608. Min Act: -0.1700

Data Index: 1152411 (Open Web Text)

Max Activating Token Index: 973