Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 71 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1483. Min Range: -8.1483
Max Act: 8.1483. Min Act: -0.1700
Data Index: 8445980 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.7108. Min Act: -0.1700
Data Index: 1908614 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.5858. Min Act: -0.1700
Data Index: 5803124 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.5858. Min Act: -0.1700
Data Index: 8763524 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.5858. Min Act: -0.1700
Data Index: 4787050 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.5233. Min Act: -0.1700
Data Index: 2754750 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.5233. Min Act: -0.1700
Data Index: 1590377 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.5233. Min Act: -0.1700
Data Index: 8427668 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.5233. Min Act: -0.1700
Data Index: 6294787 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.5233. Min Act: -0.1700
Data Index: 3451837 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.4608. Min Act: -0.1700
Data Index: 8314252 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.4608. Min Act: -0.1700
Data Index: 8003129 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.4608. Min Act: -0.1700
Data Index: 6234998 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.4608. Min Act: -0.1700
Data Index: 626156 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.4608. Min Act: -0.1700
Data Index: 6662279 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.4608. Min Act: -0.1700
Data Index: 899599 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.4608. Min Act: -0.1700
Data Index: 1499680 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.4608. Min Act: -0.1700
Data Index: 8483560 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.4608. Min Act: -0.1700
Data Index: 6235691 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1483. Min Range: -8.1483
Max Act: 7.4608. Min Act: -0.1700
Data Index: 1361113 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19