Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0898. Min Range: -5.0898
Max Act: 5.0898. Min Act: -0.1698
Data Index: 3763414 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0898. Min Range: -5.0898
Max Act: 5.0898. Min Act: -0.1700
Data Index: 3615308 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0898. Min Range: -5.0898
Max Act: 5.0273. Min Act: -0.1700
Data Index: 2264406 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0898. Min Range: -5.0898
Max Act: 5.0586. Min Act: -0.1700
Data Index: 787279 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0898. Min Range: -5.0898
Max Act: 5.0586. Min Act: -0.1700
Data Index: 1360484 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9961. Min Act: -0.1700
Data Index: 1077706 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9961. Min Act: -0.1700
Data Index: 8732436 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9961. Min Act: -0.1700
Data Index: 7327941 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9648. Min Act: -0.1700
Data Index: 7668530 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9336. Min Act: -0.1699
Data Index: 2917094 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9336. Min Act: -0.1700
Data Index: 2122742 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9336. Min Act: -0.1700
Data Index: 2932318 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9336. Min Act: -0.1698
Data Index: 1268047 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9336. Min Act: -0.1700
Data Index: 2846964 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9336. Min Act: -0.1700
Data Index: 182716 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9023. Min Act: -0.1700
Data Index: 3956666 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9023. Min Act: -0.1700
Data Index: 7656849 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9336. Min Act: -0.1698
Data Index: 2382844 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9336. Min Act: -0.1692
Data Index: 5001536 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0898. Min Range: -5.0898
Max Act: 4.9023. Min Act: -0.1700
Data Index: 328176 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19