Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4944 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2153. Min Range: -5.2153
Max Act: 5.2153. Min Act: -0.1700
Data Index: 7865583 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2153. Min Range: -5.2153
Max Act: 5.0903. Min Act: -0.1700
Data Index: 2643840 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.9653. Min Act: -0.1700
Data Index: 5714388 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.9653. Min Act: -0.1700
Data Index: 4781793 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.9341. Min Act: -0.1700
Data Index: 5459035 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.8716. Min Act: -0.1700
Data Index: 4764276 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.9028. Min Act: -0.1700
Data Index: 5058742 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.9028. Min Act: -0.1700
Data Index: 3569470 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.9028. Min Act: -0.1700
Data Index: 948326 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.8716. Min Act: -0.1700
Data Index: 5494247 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.8091. Min Act: -0.1700
Data Index: 4956435 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.8403. Min Act: -0.1700
Data Index: 8807489 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.8403. Min Act: -0.1700
Data Index: 2581118 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.8091. Min Act: -0.1700
Data Index: 1406722 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.7778. Min Act: -0.1700
Data Index: 5536152 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.7778. Min Act: -0.1700
Data Index: 2062461 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.8091. Min Act: -0.1700
Data Index: 5580840 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.7778. Min Act: -0.1700
Data Index: 1223532 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.7778. Min Act: -0.1700
Data Index: 1948439 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2153. Min Range: -5.2153
Max Act: 4.7778. Min Act: -0.1700
Data Index: 3181062 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19