Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2162 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0555. Min Range: -5.0555
Max Act: 5.0555. Min Act: -0.1700
Data Index: 5026281 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.8993. Min Act: -0.1700
Data Index: 8004389 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.8680. Min Act: -0.1700
Data Index: 1199871 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.7743. Min Act: -0.1700
Data Index: 595128 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.7430. Min Act: -0.1700
Data Index: 1763027 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.7430. Min Act: -0.1700
Data Index: 5089662 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.7743. Min Act: -0.1700
Data Index: 6713065 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.7118. Min Act: -0.1700
Data Index: 3974884 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.6805. Min Act: -0.1700
Data Index: 4790082 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.7118. Min Act: -0.1700
Data Index: 4946808 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.7118. Min Act: -0.1700
Data Index: 675164 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.7118. Min Act: -0.1700
Data Index: 1288438 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.7118. Min Act: -0.1700
Data Index: 3149213 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.6805. Min Act: -0.1700
Data Index: 3568966 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.6493. Min Act: -0.1700
Data Index: 6374571 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.6180. Min Act: -0.1700
Data Index: 6814736 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.6180. Min Act: -0.1700
Data Index: 2172181 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.6180. Min Act: -0.1700
Data Index: 4550577 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.6493. Min Act: -0.1700
Data Index: 519624 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0555. Min Range: -5.0555
Max Act: 4.6180. Min Act: -0.1700
Data Index: 3518101 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19