Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5086 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1125. Min Range: -4.1125
Max Act: 4.1125. Min Act: -0.1700
Data Index: 3749455 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1125. Min Range: -4.1125
Max Act: 4.0812. Min Act: -0.1700
Data Index: 241141 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1125. Min Range: -4.1125
Max Act: 4.0187. Min Act: -0.1700
Data Index: 3906691 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1125. Min Range: -4.1125
Max Act: 4.0187. Min Act: -0.1700
Data Index: 6709066 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1125. Min Range: -4.1125
Max Act: 4.0187. Min Act: -0.1700
Data Index: 5331369 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9874. Min Act: -0.1700
Data Index: 8735361 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9874. Min Act: -0.1700
Data Index: 3627780 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9874. Min Act: -0.1700
Data Index: 89423 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9874. Min Act: -0.1700
Data Index: 1260087 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9562. Min Act: -0.1700
Data Index: 3640584 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9249. Min Act: -0.1700
Data Index: 5317240 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9249. Min Act: -0.1700
Data Index: 2565278 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9249. Min Act: -0.1700
Data Index: 6350001 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9249. Min Act: -0.1700
Data Index: 2565586 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9249. Min Act: -0.1700
Data Index: 1914137 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9249. Min Act: -0.1700
Data Index: 2534963 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9249. Min Act: -0.1700
Data Index: 4493532 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9249. Min Act: -0.1700
Data Index: 536040 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.8936. Min Act: -0.1700
Data Index: 5006283 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1125. Min Range: -4.1125
Max Act: 3.9249. Min Act: -0.1700
Data Index: 935895 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19