Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4580 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.5593. Min Act: -0.1700
Data Index: 5402581 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.1843. Min Act: -0.1700
Data Index: 1160807 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.1530. Min Act: -0.1700
Data Index: 5586523 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.1530. Min Act: -0.1700
Data Index: 5755525 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.1530. Min Act: -0.1700
Data Index: 8609894 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.1530. Min Act: -0.1700
Data Index: 4479867 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.1218. Min Act: -0.1700
Data Index: 1858066 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.1218. Min Act: -0.1700
Data Index: 8736307 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.1218. Min Act: -0.1700
Data Index: 8203374 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.0905. Min Act: -0.1700
Data Index: 7914525 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.0593. Min Act: -0.1700
Data Index: 8781946 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5593. Min Range: -5.5593
Max Act: 4.9968. Min Act: -0.1700
Data Index: 7095686 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5593. Min Range: -5.5593
Max Act: 5.0593. Min Act: -0.1700
Data Index: 210228 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5593. Min Range: -5.5593
Max Act: 4.9968. Min Act: -0.1700
Data Index: 1315634 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5593. Min Range: -5.5593
Max Act: 4.9968. Min Act: -0.1700
Data Index: 7312226 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5593. Min Range: -5.5593
Max Act: 4.9655. Min Act: -0.1700
Data Index: 7674611 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5593. Min Range: -5.5593
Max Act: 4.9655. Min Act: -0.1700
Data Index: 1177550 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5593. Min Range: -5.5593
Max Act: 4.9655. Min Act: -0.1700
Data Index: 5193051 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5593. Min Range: -5.5593
Max Act: 4.9655. Min Act: -0.1700
Data Index: 8657045 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5593. Min Range: -5.5593
Max Act: 4.9655. Min Act: -0.1700
Data Index: 8098286 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19