Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4638 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0664. Min Range: -9.0664
Max Act: 9.0664. Min Act: -0.1700
Data Index: 2141662 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.8164. Min Act: -0.1700
Data Index: 2596903 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.6914. Min Act: -0.1700
Data Index: 8026400 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.6914. Min Act: -0.1700
Data Index: 6308191 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.6289. Min Act: -0.1700
Data Index: 2728900 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.6289. Min Act: -0.1700
Data Index: 287913 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.5039. Min Act: -0.1700
Data Index: 1108114 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.5039. Min Act: -0.1700
Data Index: 45476 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.4414. Min Act: -0.1700
Data Index: 4719288 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.3164. Min Act: -0.1700
Data Index: 8312982 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.3164. Min Act: -0.1700
Data Index: 7489631 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.3164. Min Act: -0.1700
Data Index: 5072861 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.2539. Min Act: -0.1700
Data Index: 1403831 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.1914. Min Act: -0.1700
Data Index: 3860472 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.1914. Min Act: -0.1700
Data Index: 88412 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.1914. Min Act: -0.1700
Data Index: 1678810 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.1914. Min Act: -0.1700
Data Index: 8692489 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.1914. Min Act: -0.1700
Data Index: 176334 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.1289. Min Act: -0.1700
Data Index: 7063284 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0664. Min Range: -9.0664
Max Act: 8.1289. Min Act: -0.1700
Data Index: 4541930 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19