Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6309 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7808. Min Range: -8.7808
Max Act: 8.7808. Min Act: -0.1700
Data Index: 5791937 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7808. Min Range: -8.7808
Max Act: 8.3433. Min Act: -0.1700
Data Index: 3376973 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7808. Min Range: -8.7808
Max Act: 8.3433. Min Act: -0.1700
Data Index: 5241467 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7808. Min Range: -8.7808
Max Act: 8.1558. Min Act: -0.1700
Data Index: 6655557 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7808. Min Range: -8.7808
Max Act: 8.0308. Min Act: -0.1700
Data Index: 2015916 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7808. Min Range: -8.7808
Max Act: 8.0933. Min Act: -0.1700
Data Index: 4495136 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7808. Min Range: -8.7808
Max Act: 8.0933. Min Act: -0.1700
Data Index: 3530840 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.9683. Min Act: -0.1700
Data Index: 8732303 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.9683. Min Act: -0.1700
Data Index: 64991 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7808. Min Range: -8.7808
Max Act: 8.0308. Min Act: -0.1700
Data Index: 3231767 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7808. Min Range: -8.7808
Max Act: 8.0308. Min Act: -0.1700
Data Index: 8267282 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.9058. Min Act: -0.1700
Data Index: 2835514 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.9058. Min Act: -0.1700
Data Index: 5799874 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.9683. Min Act: -0.1700
Data Index: 5295407 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.9683. Min Act: -0.1700
Data Index: 5464535 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.9058. Min Act: -0.1700
Data Index: 6296339 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.9058. Min Act: -0.1700
Data Index: 3373236 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.9058. Min Act: -0.1700
Data Index: 1302896 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.8433. Min Act: -0.1700
Data Index: 3405316 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7808. Min Range: -8.7808
Max Act: 7.8433. Min Act: -0.1700
Data Index: 1641460 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19