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

Dataset: Open Web Text

Neuron 2715 in Layer 5

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: 3.4858. Min Range: -3.4858

Max Act: 3.4858. Min Act: -0.1700

Data Index: 8234861 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3987. Min Act: -0.1700

Data Index: 571861 (Open Web Text)

Max Activating Token Index: 129

Text #2

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.3091. Min Act: -0.1700

Data Index: 911122 (Open Web Text)

Max Activating Token Index: 112

Text #3

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.1189. Min Act: -0.1700

Data Index: 6161166 (Open Web Text)

Max Activating Token Index: 484

Text #4

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.1372. Min Act: -0.1700

Data Index: 1747900 (Open Web Text)

Max Activating Token Index: 407

Text #5

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.1558. Min Act: -0.1700

Data Index: 3301968 (Open Web Text)

Max Activating Token Index: 401

Text #6

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.1622. Min Act: -0.1700

Data Index: 1031051 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.1556. Min Act: -0.1700

Data Index: 8140922 (Open Web Text)

Max Activating Token Index: 289

Text #8

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.1408. Min Act: -0.1700

Data Index: 5582988 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.1549. Min Act: -0.1700

Data Index: 1756912 (Open Web Text)

Max Activating Token Index: 110

Text #10

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.1264. Min Act: -0.1700

Data Index: 7641188 (Open Web Text)

Max Activating Token Index: 428

Text #11

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.1220. Min Act: -0.1700

Data Index: 6985346 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.1288. Min Act: -0.1700

Data Index: 3425459 (Open Web Text)

Max Activating Token Index: 532

Text #13

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.0932. Min Act: -0.1700

Data Index: 6687562 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.0514. Min Act: -0.1700

Data Index: 686199 (Open Web Text)

Max Activating Token Index: 642

Text #15

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.0844. Min Act: -0.1700

Data Index: 7405481 (Open Web Text)

Max Activating Token Index: 193

Text #16

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.0864. Min Act: -0.1700

Data Index: 7782920 (Open Web Text)

Max Activating Token Index: 481

Text #17

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.0996. Min Act: -0.1700

Data Index: 6578134 (Open Web Text)

Max Activating Token Index: 105

Text #18

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.0890. Min Act: -0.1700

Data Index: 6069409 (Open Web Text)

Max Activating Token Index: 379

Text #19

Max Range: 3.4858. Min Range: -3.4858

Max Act: 3.0650. Min Act: -0.1700

Data Index: 1517534 (Open Web Text)

Max Activating Token Index: 966