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

Dataset: Open Web Text

Neuron 2734 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: 4.2946. Min Range: -4.2946

Max Act: 4.2855. Min Act: -0.1700

Data Index: 5342517 (Open Web Text)

Max Activating Token Index: 791

Text #1

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2927. Min Act: -0.1700

Data Index: 1156510 (Open Web Text)

Max Activating Token Index: 633

Text #2

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2946. Min Act: -0.1700

Data Index: 6179024 (Open Web Text)

Max Activating Token Index: 279

Text #3

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2149. Min Act: -0.1700

Data Index: 3359498 (Open Web Text)

Max Activating Token Index: 107

Text #4

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2341. Min Act: -0.1700

Data Index: 617745 (Open Web Text)

Max Activating Token Index: 665

Text #5

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2077. Min Act: -0.1700

Data Index: 3085789 (Open Web Text)

Max Activating Token Index: 257

Text #6

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2099. Min Act: -0.1700

Data Index: 7941275 (Open Web Text)

Max Activating Token Index: 600

Text #7

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1896. Min Act: -0.1700

Data Index: 7639576 (Open Web Text)

Max Activating Token Index: 165

Text #8

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1641. Min Act: -0.1700

Data Index: 947052 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1530. Min Act: -0.1700

Data Index: 338950 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1794. Min Act: -0.1700

Data Index: 4612949 (Open Web Text)

Max Activating Token Index: 872

Text #11

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1242. Min Act: -0.1700

Data Index: 8496846 (Open Web Text)

Max Activating Token Index: 763

Text #12

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2243. Min Act: -0.1700

Data Index: 6301687 (Open Web Text)

Max Activating Token Index: 432

Text #13

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1599. Min Act: -0.1700

Data Index: 3802791 (Open Web Text)

Max Activating Token Index: 863

Text #14

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1547. Min Act: -0.1700

Data Index: 7532598 (Open Web Text)

Max Activating Token Index: 821

Text #15

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1437. Min Act: -0.1700

Data Index: 2320407 (Open Web Text)

Max Activating Token Index: 521

Text #16

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1666. Min Act: -0.1700

Data Index: 1263235 (Open Web Text)

Max Activating Token Index: 538

Text #17

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1014. Min Act: -0.1700

Data Index: 205460 (Open Web Text)

Max Activating Token Index: 992

Text #18

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1101. Min Act: -0.1700

Data Index: 3095623 (Open Web Text)

Max Activating Token Index: 839

Text #19

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.0857. Min Act: -0.1700

Data Index: 8664254 (Open Web Text)

Max Activating Token Index: 494