Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6265 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.9100. Min Act: -0.1700
Data Index: 1917173 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.7850. Min Act: -0.1700
Data Index: 6122044 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.5975. Min Act: -0.1700
Data Index: 6863608 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.5975. Min Act: -0.1700
Data Index: 5935758 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.5350. Min Act: -0.1700
Data Index: 98602 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.4725. Min Act: -0.1700
Data Index: 4855539 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.4100. Min Act: -0.1700
Data Index: 8146648 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.3475. Min Act: -0.1700
Data Index: 4603790 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.2850. Min Act: -0.1700
Data Index: 3962159 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.0975. Min Act: -0.1700
Data Index: 509485 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.1600. Min Act: -0.1700
Data Index: 4598122 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.1600. Min Act: -0.1700
Data Index: 719396 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.0975. Min Act: -0.1700
Data Index: 1195813 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.0975. Min Act: -0.1700
Data Index: 2086197 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.0975. Min Act: -0.1700
Data Index: 3528844 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.0350. Min Act: -0.1700
Data Index: 5000537 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9100. Min Range: -10.9100
Max Act: 10.0350. Min Act: -0.1700
Data Index: 190043 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9100. Min Range: -10.9100
Max Act: 9.9725. Min Act: -0.1700
Data Index: 5628420 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9100. Min Range: -10.9100
Max Act: 9.9725. Min Act: -0.1700
Data Index: 6172043 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9100. Min Range: -10.9100
Max Act: 9.9725. Min Act: -0.1700
Data Index: 1888525 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19