Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.5923. Min Act: -0.1700
Data Index: 1747230 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.4200. Min Act: -0.1700
Data Index: 7934782 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.3730. Min Act: -0.1700
Data Index: 6051662 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.3730. Min Act: -0.1700
Data Index: 5938785 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.2945. Min Act: -0.1700
Data Index: 4825185 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.2788. Min Act: -0.1700
Data Index: 2177849 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.2317. Min Act: -0.1700
Data Index: 2547447 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.2003. Min Act: -0.1700
Data Index: 7026621 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.2003. Min Act: -0.1700
Data Index: 2594196 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.2317. Min Act: -0.1700
Data Index: 2255108 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.2474. Min Act: -0.1700
Data Index: 5072377 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.1531. Min Act: -0.1700
Data Index: 2931990 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.1688. Min Act: -0.1700
Data Index: 4374910 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.1688. Min Act: -0.1700
Data Index: 700129 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.1688. Min Act: -0.1700
Data Index: 1622291 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.0901. Min Act: -0.1700
Data Index: 5165679 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.1058. Min Act: -0.1700
Data Index: 2649096 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.1058. Min Act: -0.1700
Data Index: 8172483 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.1058. Min Act: -0.1700
Data Index: 6853095 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5923. Min Range: -3.5923
Max Act: 3.0901. Min Act: -0.1700
Data Index: 2820103 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19