Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1839. Min Range: -5.1839
Max Act: 5.1839. Min Act: -0.1700
Data Index: 4937882 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.8401. Min Act: -0.1700
Data Index: 6349604 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.7776. Min Act: -0.1700
Data Index: 2949000 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.7151. Min Act: -0.1700
Data Index: 2546664 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.6839. Min Act: -0.1700
Data Index: 1918886 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.6526. Min Act: -0.1700
Data Index: 3557957 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.6214. Min Act: -0.1700
Data Index: 6711856 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.6214. Min Act: -0.1700
Data Index: 1379146 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.6526. Min Act: -0.1700
Data Index: 5741389 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.6214. Min Act: -0.1700
Data Index: 2159879 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.5901. Min Act: -0.1700
Data Index: 4931343 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.5901. Min Act: -0.1700
Data Index: 4618874 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.5901. Min Act: -0.1700
Data Index: 4223531 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.5901. Min Act: -0.1700
Data Index: 5683411 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.5901. Min Act: -0.1700
Data Index: 5915350 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.5901. Min Act: -0.1700
Data Index: 8336311 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.5589. Min Act: -0.1700
Data Index: 3389263 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.5589. Min Act: -0.1700
Data Index: 3469515 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.5589. Min Act: -0.1700
Data Index: 7599495 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1839. Min Range: -5.1839
Max Act: 4.5589. Min Act: -0.1700
Data Index: 3519468 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19