Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3794 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1526. Min Range: -6.1526
Max Act: 6.1526. Min Act: -0.1700
Data Index: 2860555 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1526. Min Range: -6.1526
Max Act: 6.0901. Min Act: -0.1700
Data Index: 2646185 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1526. Min Range: -6.1526
Max Act: 6.0588. Min Act: -0.1700
Data Index: 7248971 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1526. Min Range: -6.1526
Max Act: 6.0276. Min Act: -0.1700
Data Index: 3542084 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1526. Min Range: -6.1526
Max Act: 6.0276. Min Act: -0.1700
Data Index: 2026544 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.8713. Min Act: -0.1700
Data Index: 6795588 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.8401. Min Act: -0.1700
Data Index: 3743367 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.8713. Min Act: -0.1700
Data Index: 7588058 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.7776. Min Act: -0.1700
Data Index: 1861799 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.8401. Min Act: -0.1700
Data Index: 4474144 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.8401. Min Act: -0.1700
Data Index: 3919854 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.7463. Min Act: -0.1700
Data Index: 8204259 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.7776. Min Act: -0.1700
Data Index: 4382411 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.7463. Min Act: -0.1700
Data Index: 8474867 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.7151. Min Act: -0.1700
Data Index: 865166 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.7463. Min Act: -0.1700
Data Index: 8428732 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.7463. Min Act: -0.1700
Data Index: 7984431 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.6838. Min Act: -0.1700
Data Index: 1638488 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.7151. Min Act: -0.1700
Data Index: 1049206 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1526. Min Range: -6.1526
Max Act: 5.6838. Min Act: -0.1700
Data Index: 6443701 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19