Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0688. Min Range: -6.0688
Max Act: 6.0688. Min Act: -0.1700
Data Index: 5740861 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.9751. Min Act: -0.1700
Data Index: 1941739 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.7876. Min Act: -0.1700
Data Index: 5944590 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.7563. Min Act: -0.1700
Data Index: 6979227 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.7251. Min Act: -0.1700
Data Index: 6484269 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.7563. Min Act: -0.1700
Data Index: 1736056 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.7251. Min Act: -0.1700
Data Index: 1964281 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.7251. Min Act: -0.1700
Data Index: 4133798 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.7563. Min Act: -0.1700
Data Index: 8455612 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.7563. Min Act: -0.1700
Data Index: 7511425 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.7563. Min Act: -0.1700
Data Index: 6436962 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.6938. Min Act: -0.1700
Data Index: 2631080 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.6938. Min Act: -0.1700
Data Index: 1410181 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.6626. Min Act: -0.1700
Data Index: 3541208 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.6626. Min Act: -0.1700
Data Index: 8478006 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.6938. Min Act: -0.1700
Data Index: 6492363 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.6626. Min Act: -0.1700
Data Index: 1824213 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.6626. Min Act: -0.1700
Data Index: 5661485 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.6938. Min Act: -0.1700
Data Index: 6633575 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0688. Min Range: -6.0688
Max Act: 5.6313. Min Act: -0.1700
Data Index: 5540001 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19