Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3795. Min Range: -7.3795
Max Act: 7.3795. Min Act: -0.1700
Data Index: 3736589 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3795. Min Range: -7.3795
Max Act: 7.2858. Min Act: -0.1700
Data Index: 60835 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3795. Min Range: -7.3795
Max Act: 7.0983. Min Act: -0.1700
Data Index: 5773361 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3795. Min Range: -7.3795
Max Act: 7.0670. Min Act: -0.1700
Data Index: 481841 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3795. Min Range: -7.3795
Max Act: 7.0045. Min Act: -0.1700
Data Index: 5202573 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.9733. Min Act: -0.1700
Data Index: 7885434 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.9420. Min Act: -0.1700
Data Index: 6403407 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.7858. Min Act: -0.1700
Data Index: 7378274 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.7545. Min Act: -0.1700
Data Index: 3602574 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.7233. Min Act: -0.1700
Data Index: 1067135 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.7545. Min Act: -0.1700
Data Index: 4691577 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.6920. Min Act: -0.1700
Data Index: 6134549 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.6608. Min Act: -0.1700
Data Index: 6383198 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.6608. Min Act: -0.1700
Data Index: 7830751 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.6608. Min Act: -0.1699
Data Index: 7782106 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.6608. Min Act: -0.1700
Data Index: 4718347 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.6608. Min Act: -0.1700
Data Index: 3748131 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.6608. Min Act: -0.1700
Data Index: 7298572 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.6295. Min Act: -0.1700
Data Index: 5152137 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3795. Min Range: -7.3795
Max Act: 6.5983. Min Act: -0.1700
Data Index: 114509 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19