Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3837 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.5095. Min Act: -0.1700
Data Index: 269316 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.1970. Min Act: -0.1700
Data Index: 6639210 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.1345. Min Act: -0.1700
Data Index: 3292094 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.1345. Min Act: -0.1700
Data Index: 4659000 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.0720. Min Act: -0.1700
Data Index: 8508343 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.0408. Min Act: -0.1700
Data Index: 120426 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.0720. Min Act: -0.1700
Data Index: 173874 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.0720. Min Act: -0.1700
Data Index: 5850980 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.0408. Min Act: -0.1700
Data Index: 7130296 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.0408. Min Act: -0.1700
Data Index: 3297878 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.0408. Min Act: -0.1700
Data Index: 7240888 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.0408. Min Act: -0.1700
Data Index: 4279148 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5095. Min Range: -5.5095
Max Act: 5.0408. Min Act: -0.1700
Data Index: 7575560 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5095. Min Range: -5.5095
Max Act: 4.9783. Min Act: -0.1700
Data Index: 5759131 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5095. Min Range: -5.5095
Max Act: 4.9783. Min Act: -0.1700
Data Index: 7173429 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5095. Min Range: -5.5095
Max Act: 4.9783. Min Act: -0.1700
Data Index: 919827 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5095. Min Range: -5.5095
Max Act: 4.9783. Min Act: -0.1700
Data Index: 7216104 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5095. Min Range: -5.5095
Max Act: 4.9470. Min Act: -0.1700
Data Index: 3920636 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5095. Min Range: -5.5095
Max Act: 4.9783. Min Act: -0.1700
Data Index: 2501681 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5095. Min Range: -5.5095
Max Act: 4.9783. Min Act: -0.1700
Data Index: 7373678 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19