Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2109. Min Range: -6.2109
Max Act: 6.1797. Min Act: -0.1700
Data Index: 2872930 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2109. Min Range: -6.2109
Max Act: 6.2109. Min Act: -0.1700
Data Index: 706906 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2109. Min Range: -6.2109
Max Act: 6.1484. Min Act: -0.1700
Data Index: 312369 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2109. Min Range: -6.2109
Max Act: 6.1484. Min Act: -0.1700
Data Index: 3170009 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2109. Min Range: -6.2109
Max Act: 6.0547. Min Act: -0.1700
Data Index: 2992558 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2109. Min Range: -6.2109
Max Act: 6.0547. Min Act: -0.1700
Data Index: 522874 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.9609. Min Act: -0.1700
Data Index: 2529025 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.9922. Min Act: -0.1700
Data Index: 7870260 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.9922. Min Act: -0.1700
Data Index: 3491226 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.9609. Min Act: -0.1700
Data Index: 4588458 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.9609. Min Act: -0.1700
Data Index: 2808031 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.9297. Min Act: -0.1700
Data Index: 2594845 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.9297. Min Act: -0.1700
Data Index: 8802355 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.9297. Min Act: -0.1700
Data Index: 1988866 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.8672. Min Act: -0.1700
Data Index: 8508964 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.8672. Min Act: -0.1700
Data Index: 4555458 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.8359. Min Act: -0.1700
Data Index: 35781 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.8047. Min Act: -0.1700
Data Index: 5175136 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.8047. Min Act: -0.1700
Data Index: 7832077 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2109. Min Range: -6.2109
Max Act: 5.7734. Min Act: -0.1700
Data Index: 5781705 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19