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

Dataset: Open Web Text

Neuron 1440 in Layer 1

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: 1.8063. Min Range: -1.8063

Max Act: 1.8063. Min Act: -0.1700

Data Index: 5001122 (Open Web Text)

Max Activating Token Index: 436

Text #1

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7867. Min Act: -0.1700

Data Index: 6155463 (Open Web Text)

Max Activating Token Index: 708

Text #2

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7898. Min Act: -0.1700

Data Index: 397958 (Open Web Text)

Max Activating Token Index: 277

Text #3

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7493. Min Act: -0.1700

Data Index: 6485672 (Open Web Text)

Max Activating Token Index: 820

Text #4

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7779. Min Act: -0.1700

Data Index: 6376879 (Open Web Text)

Max Activating Token Index: 252

Text #5

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7463. Min Act: -0.1700

Data Index: 1280859 (Open Web Text)

Max Activating Token Index: 207

Text #6

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7606. Min Act: -0.1700

Data Index: 85213 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7527. Min Act: -0.1700

Data Index: 3691320 (Open Web Text)

Max Activating Token Index: 501

Text #8

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7508. Min Act: -0.1700

Data Index: 7371502 (Open Web Text)

Max Activating Token Index: 80

Text #9

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7441. Min Act: -0.1700

Data Index: 5790055 (Open Web Text)

Max Activating Token Index: 487

Text #10

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7363. Min Act: -0.1700

Data Index: 5953751 (Open Web Text)

Max Activating Token Index: 241

Text #11

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7413. Min Act: -0.1700

Data Index: 2457319 (Open Web Text)

Max Activating Token Index: 346

Text #12

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7252. Min Act: -0.1700

Data Index: 3722581 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7303. Min Act: -0.1700

Data Index: 4145848 (Open Web Text)

Max Activating Token Index: 341

Text #14

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7288. Min Act: -0.1700

Data Index: 7255454 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7105. Min Act: -0.1700

Data Index: 7106826 (Open Web Text)

Max Activating Token Index: 1014

Text #16

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7151. Min Act: -0.1700

Data Index: 5500796 (Open Web Text)

Max Activating Token Index: 68

Text #17

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7250. Min Act: -0.1700

Data Index: 1670706 (Open Web Text)

Max Activating Token Index: 602

Text #18

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7183. Min Act: -0.1700

Data Index: 7928831 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7157. Min Act: -0.1700

Data Index: 241895 (Open Web Text)

Max Activating Token Index: 508