Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4510 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2660. Min Range: -6.2660
Max Act: 6.2035. Min Act: -0.1700
Data Index: 3991614 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2660. Min Range: -6.2660
Max Act: 6.2660. Min Act: -0.1700
Data Index: 8556111 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2660. Min Range: -6.2660
Max Act: 6.0473. Min Act: -0.1700
Data Index: 775985 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.9848. Min Act: -0.1700
Data Index: 1083934 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.9848. Min Act: -0.1700
Data Index: 8676056 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.9848. Min Act: -0.1700
Data Index: 231270 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.9223. Min Act: -0.1700
Data Index: 4760879 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.8910. Min Act: -0.1700
Data Index: 498309 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.8598. Min Act: -0.1700
Data Index: 1182149 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.8598. Min Act: -0.1700
Data Index: 8444674 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.8598. Min Act: -0.1700
Data Index: 1714388 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.7973. Min Act: -0.1700
Data Index: 8548398 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.7973. Min Act: -0.1700
Data Index: 4673863 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.8285. Min Act: -0.1700
Data Index: 6265971 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.7973. Min Act: -0.1700
Data Index: 7248823 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.7973. Min Act: -0.1700
Data Index: 4813499 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.7660. Min Act: -0.1700
Data Index: 1181977 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.7660. Min Act: -0.1700
Data Index: 8657917 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.7660. Min Act: -0.1700
Data Index: 2983743 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2660. Min Range: -6.2660
Max Act: 5.7348. Min Act: -0.1700
Data Index: 7546609 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19