Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5525 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.6014. Min Act: -0.1700
Data Index: 6470991 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.4764. Min Act: -0.1700
Data Index: 7710443 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.4451. Min Act: -0.1700
Data Index: 923962 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.3826. Min Act: -0.1700
Data Index: 5184342 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.3514. Min Act: -0.1700
Data Index: 589941 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.3201. Min Act: -0.1700
Data Index: 8746007 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.3201. Min Act: -0.1700
Data Index: 4288293 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.3201. Min Act: -0.1700
Data Index: 8236016 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.2889. Min Act: -0.1700
Data Index: 4399218 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.2889. Min Act: -0.1700
Data Index: 7226658 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.2889. Min Act: -0.1700
Data Index: 2796323 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.2576. Min Act: -0.1700
Data Index: 1159713 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.2889. Min Act: -0.1700
Data Index: 626254 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.1639. Min Act: -0.1700
Data Index: 2813346 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.1639. Min Act: -0.1700
Data Index: 1848510 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.1014. Min Act: -0.1700
Data Index: 5982858 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.0701. Min Act: -0.1700
Data Index: 7742625 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.0389. Min Act: -0.1700
Data Index: 2506571 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.0701. Min Act: -0.1700
Data Index: 1723178 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6014. Min Range: -7.6014
Max Act: 7.0389. Min Act: -0.1700
Data Index: 2899516 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19