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

Dataset: Open Web Text

Neuron 1504 in Layer 3

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: 5.1933. Min Range: -5.1933

Max Act: 5.1933. Min Act: -0.1700

Data Index: 3123139 (Open Web Text)

Max Activating Token Index: 640

Text #1

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.9171. Min Act: -0.1700

Data Index: 5162048 (Open Web Text)

Max Activating Token Index: 893

Text #2

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.7518. Min Act: -0.1700

Data Index: 7663216 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.7496. Min Act: -0.1700

Data Index: 8147835 (Open Web Text)

Max Activating Token Index: 709

Text #4

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.8279. Min Act: -0.1700

Data Index: 179494 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6756. Min Act: -0.1700

Data Index: 2721233 (Open Web Text)

Max Activating Token Index: 1019

Text #6

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6900. Min Act: -0.1700

Data Index: 5730360 (Open Web Text)

Max Activating Token Index: 242

Text #7

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6307. Min Act: -0.1700

Data Index: 607595 (Open Web Text)

Max Activating Token Index: 674

Text #8

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6483. Min Act: -0.1700

Data Index: 6934149 (Open Web Text)

Max Activating Token Index: 856

Text #9

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6905. Min Act: -0.1700

Data Index: 8824490 (Open Web Text)

Max Activating Token Index: 1009

Text #10

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.7203. Min Act: -0.1700

Data Index: 3666487 (Open Web Text)

Max Activating Token Index: 973

Text #11

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6861. Min Act: -0.1700

Data Index: 6321947 (Open Web Text)

Max Activating Token Index: 943

Text #12

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.5937. Min Act: -0.1700

Data Index: 1607612 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6594. Min Act: -0.1700

Data Index: 2759765 (Open Web Text)

Max Activating Token Index: 287

Text #14

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6731. Min Act: -0.1700

Data Index: 8426969 (Open Web Text)

Max Activating Token Index: 509

Text #15

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6670. Min Act: -0.1700

Data Index: 6445346 (Open Web Text)

Max Activating Token Index: 305

Text #16

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6262. Min Act: -0.1700

Data Index: 5261545 (Open Web Text)

Max Activating Token Index: 171

Text #17

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6480. Min Act: -0.1700

Data Index: 1143988 (Open Web Text)

Max Activating Token Index: 517

Text #18

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6179. Min Act: -0.1700

Data Index: 1313599 (Open Web Text)

Max Activating Token Index: 541

Text #19

Max Range: 5.1933. Min Range: -5.1933

Max Act: 4.6301. Min Act: -0.1700

Data Index: 2314588 (Open Web Text)

Max Activating Token Index: 286