Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3618 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.7415. Min Act: -0.1700
Data Index: 1785138 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.7415. Min Act: -0.1700
Data Index: 6418918 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.7571. Min Act: -0.1700
Data Index: 2757619 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.7415. Min Act: -0.1700
Data Index: 4997314 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6946. Min Act: -0.1700
Data Index: 843507 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6946. Min Act: -0.1700
Data Index: 6387525 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6789. Min Act: -0.1700
Data Index: 3251464 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6476. Min Act: -0.1700
Data Index: 2016533 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6476. Min Act: -0.1700
Data Index: 3566040 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6476. Min Act: -0.1700
Data Index: 6580632 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6476. Min Act: -0.1700
Data Index: 230132 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6476. Min Act: -0.1700
Data Index: 1670732 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6476. Min Act: -0.1700
Data Index: 1642711 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6320. Min Act: -0.1700
Data Index: 577953 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6320. Min Act: -0.1700
Data Index: 252133 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6476. Min Act: -0.1700
Data Index: 83802 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6320. Min Act: -0.1700
Data Index: 933433 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6320. Min Act: -0.1700
Data Index: 5722603 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6163. Min Act: -0.1700
Data Index: 5734606 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7571. Min Range: -3.7571
Max Act: 3.6320. Min Act: -0.1700
Data Index: 4811958 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19