Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4709 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.2708. Min Act: -0.1700
Data Index: 8434871 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.2396. Min Act: -0.1700
Data Index: 5561724 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.2083. Min Act: -0.1700
Data Index: 5107488 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.1771. Min Act: -0.1700
Data Index: 3354279 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.2083. Min Act: -0.1700
Data Index: 5923048 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.1458. Min Act: -0.1700
Data Index: 7536530 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.0833. Min Act: -0.1700
Data Index: 7982688 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.1146. Min Act: -0.1700
Data Index: 8588199 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.0833. Min Act: -0.1700
Data Index: 1556356 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.0521. Min Act: -0.1700
Data Index: 7366997 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.0208. Min Act: -0.1700
Data Index: 7369464 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.0208. Min Act: -0.1700
Data Index: 400847 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.0208. Min Act: -0.1700
Data Index: 4365256 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.0208. Min Act: -0.1700
Data Index: 6400436 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2708. Min Range: -6.2708
Max Act: 5.9896. Min Act: -0.1700
Data Index: 1226862 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2708. Min Range: -6.2708
Max Act: 5.9896. Min Act: -0.1699
Data Index: 5601671 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2708. Min Range: -6.2708
Max Act: 5.9583. Min Act: -0.1700
Data Index: 6106329 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2708. Min Range: -6.2708
Max Act: 6.0208. Min Act: -0.1700
Data Index: 2776355 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2708. Min Range: -6.2708
Max Act: 5.9896. Min Act: -0.1700
Data Index: 576993 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2708. Min Range: -6.2708
Max Act: 5.9896. Min Act: -0.1700
Data Index: 2029864 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19