Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4327 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0785. Min Range: -7.0785
Max Act: 7.0785. Min Act: -0.1700
Data Index: 7862667 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.5160. Min Act: -0.1700
Data Index: 680240 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.3285. Min Act: -0.1700
Data Index: 1817811 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.2660. Min Act: -0.1700
Data Index: 6564019 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.2035. Min Act: -0.1700
Data Index: 8725846 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.2035. Min Act: -0.1700
Data Index: 4505062 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.1722. Min Act: -0.1700
Data Index: 5469586 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.1722. Min Act: -0.1700
Data Index: 5709459 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.1410. Min Act: -0.1700
Data Index: 4826112 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.1410. Min Act: -0.1700
Data Index: 6813975 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.1097. Min Act: -0.1700
Data Index: 4291886 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.0785. Min Act: -0.1700
Data Index: 7649502 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.0785. Min Act: -0.1700
Data Index: 61619 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.0785. Min Act: -0.1700
Data Index: 878909 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0785. Min Range: -7.0785
Max Act: 6.0160. Min Act: -0.1700
Data Index: 2367610 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0785. Min Range: -7.0785
Max Act: 5.9535. Min Act: -0.1700
Data Index: 2379994 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0785. Min Range: -7.0785
Max Act: 5.9535. Min Act: -0.1700
Data Index: 398048 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0785. Min Range: -7.0785
Max Act: 5.9535. Min Act: -0.1700
Data Index: 7920061 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0785. Min Range: -7.0785
Max Act: 5.9847. Min Act: -0.1700
Data Index: 2419584 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0785. Min Range: -7.0785
Max Act: 5.9222. Min Act: -0.1700
Data Index: 5491901 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19