Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2560. Min Range: -6.2560
Max Act: 6.2560. Min Act: -0.1700
Data Index: 5292393 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2560. Min Range: -6.2560
Max Act: 6.1622. Min Act: -0.1700
Data Index: 4012545 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2560. Min Range: -6.2560
Max Act: 6.1310. Min Act: -0.1700
Data Index: 2877236 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2560. Min Range: -6.2560
Max Act: 6.0685. Min Act: -0.1700
Data Index: 3941887 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.9435. Min Act: -0.1700
Data Index: 1013992 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.9435. Min Act: -0.1700
Data Index: 431770 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.9435. Min Act: -0.1700
Data Index: 1660502 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.9435. Min Act: -0.1700
Data Index: 4270591 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.7560. Min Act: -0.1700
Data Index: 1629576 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.7247. Min Act: -0.1700
Data Index: 3911869 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.6622. Min Act: -0.1700
Data Index: 864742 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.6622. Min Act: -0.1700
Data Index: 963269 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.6622. Min Act: -0.1700
Data Index: 6417767 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.6310. Min Act: -0.1700
Data Index: 3803716 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.5997. Min Act: -0.1700
Data Index: 8748498 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.5997. Min Act: -0.1700
Data Index: 1428647 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.5685. Min Act: -0.1700
Data Index: 6911543 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.5685. Min Act: -0.1700
Data Index: 3947780 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.5372. Min Act: -0.1700
Data Index: 7238309 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.5685. Min Act: -0.1700
Data Index: 3958153 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19