Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5177 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.8437. Min Act: -0.1700
Data Index: 5581311 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.7812. Min Act: -0.1700
Data Index: 8539577 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.6249. Min Act: -0.1700
Data Index: 7610305 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.5937. Min Act: -0.1700
Data Index: 3550290 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.5937. Min Act: -0.1700
Data Index: 8450539 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.4999. Min Act: -0.1700
Data Index: 4526456 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.4687. Min Act: -0.1700
Data Index: 3544722 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.4062. Min Act: -0.1700
Data Index: 5657874 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.4062. Min Act: -0.1700
Data Index: 1335703 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.3749. Min Act: -0.1700
Data Index: 1744075 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.3749. Min Act: -0.1700
Data Index: 2874247 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.3749. Min Act: -0.1700
Data Index: 3541183 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.3437. Min Act: -0.1700
Data Index: 1314425 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.3124. Min Act: -0.1700
Data Index: 2386904 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.3124. Min Act: -0.1700
Data Index: 5941078 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.3124. Min Act: -0.1700
Data Index: 8438165 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.3124. Min Act: -0.1700
Data Index: 2211745 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.2812. Min Act: -0.1700
Data Index: 650382 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.3124. Min Act: -0.1700
Data Index: 7515932 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8437. Min Range: -6.8437
Max Act: 6.3437. Min Act: -0.1700
Data Index: 2065493 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19