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

Dataset: Open Web Text

Neuron 808 in Layer 0

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: 1.2952. Min Range: -1.2952

Max Act: 1.2837. Min Act: -0.1700

Data Index: 1592321 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2952. Min Act: -0.1700

Data Index: 5077383 (Open Web Text)

Max Activating Token Index: 888

Text #2

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2638. Min Act: -0.1700

Data Index: 204931 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2877. Min Act: -0.1700

Data Index: 3661207 (Open Web Text)

Max Activating Token Index: 536

Text #4

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2626. Min Act: -0.1700

Data Index: 1724449 (Open Web Text)

Max Activating Token Index: 755

Text #5

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2562. Min Act: -0.1700

Data Index: 5741158 (Open Web Text)

Max Activating Token Index: 736

Text #6

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2688. Min Act: -0.1700

Data Index: 1620252 (Open Web Text)

Max Activating Token Index: 558

Text #7

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2480. Min Act: -0.1700

Data Index: 8580919 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2529. Min Act: -0.1700

Data Index: 3072018 (Open Web Text)

Max Activating Token Index: 999

Text #9

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2415. Min Act: -0.1700

Data Index: 7319617 (Open Web Text)

Max Activating Token Index: 846

Text #10

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2406. Min Act: -0.1700

Data Index: 706417 (Open Web Text)

Max Activating Token Index: 287

Text #11

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2437. Min Act: -0.1700

Data Index: 7418191 (Open Web Text)

Max Activating Token Index: 718

Text #12

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2326. Min Act: -0.1700

Data Index: 2040608 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2455. Min Act: -0.1700

Data Index: 5395652 (Open Web Text)

Max Activating Token Index: 708

Text #14

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2273. Min Act: -0.1700

Data Index: 2673578 (Open Web Text)

Max Activating Token Index: 248

Text #15

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2170. Min Act: -0.1698

Data Index: 4292847 (Open Web Text)

Max Activating Token Index: 927

Text #16

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2084. Min Act: -0.1700

Data Index: 6073873 (Open Web Text)

Max Activating Token Index: 922

Text #17

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2161. Min Act: -0.1700

Data Index: 3286119 (Open Web Text)

Max Activating Token Index: 818

Text #18

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.1999. Min Act: -0.1700

Data Index: 2297749 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.1942. Min Act: -0.1700

Data Index: 443566 (Open Web Text)

Max Activating Token Index: 929