Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.7830. Min Act: -0.1700
Data Index: 5683888 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.7518. Min Act: -0.1700
Data Index: 6875900 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.7518. Min Act: -0.1700
Data Index: 7302800 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.6893. Min Act: -0.1700
Data Index: 1616968 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.7205. Min Act: -0.1700
Data Index: 7742263 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.6893. Min Act: -0.1700
Data Index: 271767 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.6893. Min Act: -0.1700
Data Index: 3765750 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.6893. Min Act: -0.1700
Data Index: 4521041 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.6268. Min Act: -0.1700
Data Index: 8383436 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.6268. Min Act: -0.1700
Data Index: 1291471 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5955. Min Act: -0.1700
Data Index: 1353495 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5955. Min Act: -0.1700
Data Index: 8462635 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5955. Min Act: -0.1700
Data Index: 1513570 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5643. Min Act: -0.1700
Data Index: 2113439 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5643. Min Act: -0.1700
Data Index: 2064793 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5955. Min Act: -0.1700
Data Index: 4004270 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5643. Min Act: -0.1700
Data Index: 1522850 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5643. Min Act: -0.1700
Data Index: 4442648 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5330. Min Act: -0.1700
Data Index: 7269218 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7830. Min Range: -4.7830
Max Act: 4.5643. Min Act: -0.1700
Data Index: 6494789 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19