Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1503 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0558. Min Range: -6.0558
Max Act: 6.0558. Min Act: -0.1700
Data Index: 4781673 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.7433. Min Act: -0.1700
Data Index: 7322234 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.6183. Min Act: -0.1700
Data Index: 5560174 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.5558. Min Act: -0.1700
Data Index: 2253018 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.5558. Min Act: -0.1700
Data Index: 7018044 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.5246. Min Act: -0.1700
Data Index: 5980059 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.5246. Min Act: -0.1700
Data Index: 7224338 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.4933. Min Act: -0.1700
Data Index: 1475513 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.4621. Min Act: -0.1700
Data Index: 3201983 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.4621. Min Act: -0.1700
Data Index: 4781674 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.4621. Min Act: -0.1700
Data Index: 4496922 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.4621. Min Act: -0.1700
Data Index: 2058848 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.4308. Min Act: -0.1700
Data Index: 5010148 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.4308. Min Act: -0.1700
Data Index: 5119663 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.4308. Min Act: -0.1700
Data Index: 6716953 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.4308. Min Act: -0.1700
Data Index: 8443905 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.3996. Min Act: -0.1700
Data Index: 5397344 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.3371. Min Act: -0.1700
Data Index: 1962447 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.3683. Min Act: -0.1700
Data Index: 4024152 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0558. Min Range: -6.0558
Max Act: 5.3683. Min Act: -0.1700
Data Index: 1986062 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19