Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0830. Min Range: -6.0830
Max Act: 6.0517. Min Act: -0.1700
Data Index: 6974935 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0830. Min Range: -6.0830
Max Act: 6.0830. Min Act: -0.1700
Data Index: 851386 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.9580. Min Act: -0.1700
Data Index: 1303858 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.9580. Min Act: -0.1700
Data Index: 293224 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.9892. Min Act: -0.1700
Data Index: 12292 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.9267. Min Act: -0.1700
Data Index: 557054 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.8642. Min Act: -0.1700
Data Index: 5941267 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.8642. Min Act: -0.1700
Data Index: 7790177 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.8642. Min Act: -0.1700
Data Index: 2966970 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.8642. Min Act: -0.1700
Data Index: 5618587 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.8330. Min Act: -0.1700
Data Index: 7192270 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.8017. Min Act: -0.1700
Data Index: 6503266 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.8017. Min Act: -0.1700
Data Index: 5485989 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.8330. Min Act: -0.1700
Data Index: 6822957 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.7705. Min Act: -0.1700
Data Index: 7098186 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.8017. Min Act: -0.1700
Data Index: 4321053 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.7705. Min Act: -0.1700
Data Index: 7820162 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.8017. Min Act: -0.1700
Data Index: 7411606 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.7705. Min Act: -0.1700
Data Index: 4839945 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0830. Min Range: -6.0830
Max Act: 5.7705. Min Act: -0.1700
Data Index: 6242647 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19