Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.6187. Min Act: -0.1700
Data Index: 3931337 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.4624. Min Act: -0.1700
Data Index: 1849208 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.2124. Min Act: -0.1700
Data Index: 4157687 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.1499. Min Act: -0.1700
Data Index: 5290941 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.0874. Min Act: -0.1700
Data Index: 2775549 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.0562. Min Act: -0.1700
Data Index: 7673443 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.0874. Min Act: -0.1700
Data Index: 1187654 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.0874. Min Act: -0.1700
Data Index: 8077787 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.0249. Min Act: -0.1700
Data Index: 4959109 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.0249. Min Act: -0.1700
Data Index: 8657668 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6187. Min Range: -7.6187
Max Act: 6.9937. Min Act: -0.1700
Data Index: 3550833 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.0249. Min Act: -0.1700
Data Index: 3034757 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.0562. Min Act: -0.1700
Data Index: 9522 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6187. Min Range: -7.6187
Max Act: 7.0249. Min Act: -0.1700
Data Index: 6695739 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6187. Min Range: -7.6187
Max Act: 6.9937. Min Act: -0.1700
Data Index: 7404527 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6187. Min Range: -7.6187
Max Act: 6.9937. Min Act: -0.1700
Data Index: 5225395 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6187. Min Range: -7.6187
Max Act: 6.9624. Min Act: -0.1700
Data Index: 6491939 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6187. Min Range: -7.6187
Max Act: 6.9312. Min Act: -0.1700
Data Index: 6437035 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6187. Min Range: -7.6187
Max Act: 6.9624. Min Act: -0.1700
Data Index: 6564368 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6187. Min Range: -7.6187
Max Act: 6.9312. Min Act: -0.1700
Data Index: 2983134 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19