Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.9090. Min Act: -0.1700
Data Index: 6675668 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.8778. Min Act: -0.1700
Data Index: 697798 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.8465. Min Act: -0.1700
Data Index: 22812 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.8153. Min Act: -0.1700
Data Index: 5786679 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.8153. Min Act: -0.1700
Data Index: 5157609 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.7528. Min Act: -0.1700
Data Index: 6560730 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.7528. Min Act: -0.1700
Data Index: 8518428 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.7215. Min Act: -0.1700
Data Index: 4381946 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.6903. Min Act: -0.1700
Data Index: 3082725 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.6903. Min Act: -0.1700
Data Index: 1214694 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.6590. Min Act: -0.1700
Data Index: 4406374 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.6278. Min Act: -0.1700
Data Index: 5568993 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.6278. Min Act: -0.1700
Data Index: 5001129 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.5965. Min Act: -0.1700
Data Index: 6675681 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.6278. Min Act: -0.1700
Data Index: 5001122 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.6278. Min Act: -0.1700
Data Index: 1125502 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.6278. Min Act: -0.1700
Data Index: 1395092 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.6278. Min Act: -0.1700
Data Index: 3859533 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.5965. Min Act: -0.1700
Data Index: 3721854 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9090. Min Range: -5.9090
Max Act: 5.5965. Min Act: -0.1700
Data Index: 744103 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19