Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.6810. Min Act: -0.1700
Data Index: 7161731 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.6497. Min Act: -0.1700
Data Index: 6402952 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.6184. Min Act: -0.1700
Data Index: 8462801 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.6028. Min Act: -0.1700
Data Index: 6155901 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.5715. Min Act: -0.1700
Data Index: 1697633 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.5558. Min Act: -0.1700
Data Index: 6923899 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.5245. Min Act: -0.1700
Data Index: 7959480 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.5401. Min Act: -0.1700
Data Index: 605535 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.5401. Min Act: -0.1700
Data Index: 2611709 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.5401. Min Act: -0.1700
Data Index: 7577624 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4932. Min Act: -0.1700
Data Index: 4764162 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4932. Min Act: -0.1700
Data Index: 1980308 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4932. Min Act: -0.1700
Data Index: 4309911 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4775. Min Act: -0.1700
Data Index: 7161397 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4618. Min Act: -0.1700
Data Index: 1835672 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4462. Min Act: -0.1700
Data Index: 5062686 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4462. Min Act: -0.1700
Data Index: 3655587 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4305. Min Act: -0.1700
Data Index: 2854947 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4148. Min Act: -0.1700
Data Index: 3962716 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4148. Min Act: -0.1700
Data Index: 2483173 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19