Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2537 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2936. Min Range: -5.2936
Max Act: 5.2936. Min Act: -0.1700
Data Index: 6083826 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2936. Min Range: -5.2936
Max Act: 5.1374. Min Act: -0.1700
Data Index: 4436956 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2936. Min Range: -5.2936
Max Act: 5.0124. Min Act: -0.1700
Data Index: 5767902 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2936. Min Range: -5.2936
Max Act: 5.0749. Min Act: -0.1700
Data Index: 8050340 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2936. Min Range: -5.2936
Max Act: 5.0124. Min Act: -0.1700
Data Index: 5469777 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9499. Min Act: -0.1700
Data Index: 3221755 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9811. Min Act: -0.1700
Data Index: 4321107 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9811. Min Act: -0.1700
Data Index: 5242296 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9811. Min Act: -0.1700
Data Index: 5332138 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9499. Min Act: -0.1700
Data Index: 6288413 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9186. Min Act: -0.1700
Data Index: 8176684 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9499. Min Act: -0.1699
Data Index: 8599603 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9499. Min Act: -0.1700
Data Index: 4940932 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9186. Min Act: -0.1700
Data Index: 167327 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.8874. Min Act: -0.1700
Data Index: 6908082 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9186. Min Act: -0.1699
Data Index: 3080414 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9186. Min Act: -0.1700
Data Index: 8140286 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9186. Min Act: -0.1700
Data Index: 1952998 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.9186. Min Act: -0.1700
Data Index: 943184 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2936. Min Range: -5.2936
Max Act: 4.8874. Min Act: -0.1700
Data Index: 5219223 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19