Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1086. Min Range: -7.1086
Max Act: 7.1086. Min Act: -0.1700
Data Index: 303892 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1086. Min Range: -7.1086
Max Act: 7.0461. Min Act: -0.1700
Data Index: 2708824 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1086. Min Range: -7.1086
Max Act: 7.0461. Min Act: -0.1700
Data Index: 613571 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1086. Min Range: -7.1086
Max Act: 7.0148. Min Act: -0.1700
Data Index: 4463191 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.9523. Min Act: -0.1700
Data Index: 6981001 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.9211. Min Act: -0.1700
Data Index: 8254131 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.9523. Min Act: -0.1700
Data Index: 1127280 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.9523. Min Act: -0.1700
Data Index: 3112099 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.9211. Min Act: -0.1700
Data Index: 1408041 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.8586. Min Act: -0.1700
Data Index: 2788365 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.8898. Min Act: -0.1700
Data Index: 2372562 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.8898. Min Act: -0.1700
Data Index: 3544839 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.8586. Min Act: -0.1700
Data Index: 5915136 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.8586. Min Act: -0.1700
Data Index: 2955226 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.8273. Min Act: -0.1700
Data Index: 5315810 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.7961. Min Act: -0.1700
Data Index: 1764971 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.7961. Min Act: -0.1700
Data Index: 6152574 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.7648. Min Act: -0.1700
Data Index: 1405320 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.7648. Min Act: -0.1700
Data Index: 7498611 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1086. Min Range: -7.1086
Max Act: 6.7648. Min Act: -0.1700
Data Index: 988537 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19