Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1836 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.3939. Min Act: -0.1700
Data Index: 5713210 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.3626. Min Act: -0.1700
Data Index: 3960160 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.2376. Min Act: -0.1700
Data Index: 724267 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.1751. Min Act: -0.1700
Data Index: 5711877 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.2064. Min Act: -0.1700
Data Index: 5515687 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.2064. Min Act: -0.1700
Data Index: 5407714 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.2064. Min Act: -0.1700
Data Index: 7520597 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.2064. Min Act: -0.1700
Data Index: 2896958 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.1439. Min Act: -0.1700
Data Index: 2938382 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.1126. Min Act: -0.1700
Data Index: 7027369 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.1126. Min Act: -0.1700
Data Index: 6132833 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.1126. Min Act: -0.1700
Data Index: 1494191 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.1126. Min Act: -0.1700
Data Index: 1135653 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.1126. Min Act: -0.1700
Data Index: 5138814 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.1126. Min Act: -0.1700
Data Index: 8817862 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.1126. Min Act: -0.1700
Data Index: 3057295 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.0814. Min Act: -0.1700
Data Index: 1282124 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.0814. Min Act: -0.1700
Data Index: 1143399 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.0814. Min Act: -0.1700
Data Index: 5714371 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3939. Min Range: -4.3939
Max Act: 4.0814. Min Act: -0.1700
Data Index: 7595068 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19