Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 922 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.9841. Min Act: -0.1700
Data Index: 3426606 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.8591. Min Act: -0.1700
Data Index: 8693051 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.8591. Min Act: -0.1700
Data Index: 212922 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.8591. Min Act: -0.1700
Data Index: 3188588 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.7654. Min Act: -0.1700
Data Index: 37089 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.7341. Min Act: -0.1700
Data Index: 2571509 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.7654. Min Act: -0.1700
Data Index: 6866569 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.7029. Min Act: -0.1700
Data Index: 7860268 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.7029. Min Act: -0.1700
Data Index: 8159518 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.7029. Min Act: -0.1700
Data Index: 5586320 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.7029. Min Act: -0.1700
Data Index: 6946946 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.7029. Min Act: -0.1700
Data Index: 3090825 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.7029. Min Act: -0.1700
Data Index: 1923166 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.6716. Min Act: -0.1700
Data Index: 4375158 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.6716. Min Act: -0.1700
Data Index: 6254853 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.6404. Min Act: -0.1700
Data Index: 2154150 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.5779. Min Act: -0.1700
Data Index: 7925558 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.6091. Min Act: -0.1700
Data Index: 4291338 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.6091. Min Act: -0.1700
Data Index: 4948170 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9841. Min Range: -4.9841
Max Act: 4.6404. Min Act: -0.1700
Data Index: 3020377 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19