Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5021 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.4259. Min Act: -0.1700
Data Index: 4024702 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.1759. Min Act: -0.1700
Data Index: 2020524 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.2071. Min Act: -0.1700
Data Index: 2076705 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.1446. Min Act: -0.1700
Data Index: 1284982 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.1759. Min Act: -0.1700
Data Index: 4059860 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.1759. Min Act: -0.1700
Data Index: 5002459 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.1446. Min Act: -0.1700
Data Index: 7582121 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.1134. Min Act: -0.1700
Data Index: 840276 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0821. Min Act: -0.1700
Data Index: 7365369 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0821. Min Act: -0.1700
Data Index: 3075431 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0821. Min Act: -0.1700
Data Index: 4333942 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0196. Min Act: -0.1700
Data Index: 4532627 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0196. Min Act: -0.1700
Data Index: 4718467 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0196. Min Act: -0.1700
Data Index: 6971077 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0196. Min Act: -0.1700
Data Index: 8601825 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4259. Min Range: -5.4259
Max Act: 5.0196. Min Act: -0.1700
Data Index: 8104613 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9884. Min Act: -0.1700
Data Index: 6322311 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9884. Min Act: -0.1700
Data Index: 6829656 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9884. Min Act: -0.1700
Data Index: 5360567 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4259. Min Range: -5.4259
Max Act: 4.9884. Min Act: -0.1700
Data Index: 5334630 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19