Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1496 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.8022. Min Act: -0.1700
Data Index: 1350791 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7710. Min Act: -0.1700
Data Index: 5567949 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7710. Min Act: -0.1700
Data Index: 283770 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7710. Min Act: -0.1700
Data Index: 4356944 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7710. Min Act: -0.1700
Data Index: 5791459 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7710. Min Act: -0.1700
Data Index: 4356955 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7397. Min Act: -0.1700
Data Index: 6129151 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7397. Min Act: -0.1700
Data Index: 6558217 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7085. Min Act: -0.1700
Data Index: 3214110 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7085. Min Act: -0.1700
Data Index: 6316453 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7085. Min Act: -0.1700
Data Index: 6247303 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7397. Min Act: -0.1700
Data Index: 2462846 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7085. Min Act: -0.1700
Data Index: 3879350 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7085. Min Act: -0.1700
Data Index: 2235144 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7085. Min Act: -0.1700
Data Index: 1950242 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7085. Min Act: -0.1700
Data Index: 582647 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7085. Min Act: -0.1700
Data Index: 1915374 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.6772. Min Act: -0.1700
Data Index: 1007498 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.6772. Min Act: -0.1700
Data Index: 1807865 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8022. Min Range: -5.8022
Max Act: 5.7085. Min Act: -0.1700
Data Index: 6247300 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19