Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2932 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.9900. Min Act: -0.1700
Data Index: 134515 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.6150. Min Act: -0.1700
Data Index: 3243779 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.4900. Min Act: -0.1700
Data Index: 683128 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.4900. Min Act: -0.1700
Data Index: 1095701 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.4275. Min Act: -0.1700
Data Index: 4977960 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.3650. Min Act: -0.1700
Data Index: 5488959 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.2400. Min Act: -0.1700
Data Index: 6383854 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.2400. Min Act: -0.1700
Data Index: 3453378 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1775. Min Act: -0.1700
Data Index: 122448 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1150. Min Act: -0.1700
Data Index: 1544110 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1775. Min Act: -0.1700
Data Index: 8133275 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1775. Min Act: -0.1700
Data Index: 2175119 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1150. Min Act: -0.1700
Data Index: 3811224 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1150. Min Act: -0.1700
Data Index: 1524431 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1150. Min Act: -0.1700
Data Index: 8578893 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1150. Min Act: -0.1700
Data Index: 7807814 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1150. Min Act: -0.1700
Data Index: 6143915 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.0525. Min Act: -0.1700
Data Index: 3783081 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.0525. Min Act: -0.1700
Data Index: 3322817 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.0525. Min Act: -0.1700
Data Index: 2861930 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19