Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4612 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3868. Min Range: -8.3868
Max Act: 8.3868. Min Act: -0.1700
Data Index: 8531373 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3868. Min Range: -8.3868
Max Act: 8.3243. Min Act: -0.1700
Data Index: 273254 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3868. Min Range: -8.3868
Max Act: 8.1680. Min Act: -0.1700
Data Index: 8708612 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3868. Min Range: -8.3868
Max Act: 8.1680. Min Act: -0.1700
Data Index: 1800084 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3868. Min Range: -8.3868
Max Act: 8.0118. Min Act: -0.1700
Data Index: 544206 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.8868. Min Act: -0.1700
Data Index: 5296485 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.9180. Min Act: -0.1700
Data Index: 8277215 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.8555. Min Act: -0.1700
Data Index: 5296484 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.8243. Min Act: -0.1700
Data Index: 5790766 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.7930. Min Act: -0.1700
Data Index: 118686 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.7930. Min Act: -0.1700
Data Index: 5083226 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.7930. Min Act: -0.1700
Data Index: 8589176 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.7618. Min Act: -0.1700
Data Index: 118682 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.7618. Min Act: -0.1700
Data Index: 118676 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.7305. Min Act: -0.1700
Data Index: 5517091 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.6368. Min Act: -0.1700
Data Index: 5306128 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.7305. Min Act: -0.1700
Data Index: 118675 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.6993. Min Act: -0.1700
Data Index: 8589177 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.6993. Min Act: -0.1700
Data Index: 118683 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3868. Min Range: -8.3868
Max Act: 7.6993. Min Act: -0.1700
Data Index: 276274 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19