Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2757 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0932. Min Range: -3.0932
Max Act: 3.0932. Min Act: -0.1700
Data Index: 6124116 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0932. Min Range: -3.0932
Max Act: 3.0459. Min Act: -0.1700
Data Index: 7115327 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0932. Min Range: -3.0932
Max Act: 3.0459. Min Act: -0.1700
Data Index: 4740427 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9827. Min Act: -0.1700
Data Index: 8695576 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0932. Min Range: -3.0932
Max Act: 3.0143. Min Act: -0.1700
Data Index: 4740417 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9985. Min Act: -0.1700
Data Index: 4118349 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9827. Min Act: -0.1700
Data Index: 5469200 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9827. Min Act: -0.1700
Data Index: 6959692 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9352. Min Act: -0.1700
Data Index: 5838 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9194. Min Act: -0.1700
Data Index: 4298162 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9511. Min Act: -0.1700
Data Index: 5178744 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9194. Min Act: -0.1700
Data Index: 891308 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9194. Min Act: -0.1700
Data Index: 4018494 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9194. Min Act: -0.1700
Data Index: 7164655 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9194. Min Act: -0.1700
Data Index: 575060 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9035. Min Act: -0.1700
Data Index: 2353996 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.8877. Min Act: -0.1700
Data Index: 4331125 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9035. Min Act: -0.1700
Data Index: 2971549 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9035. Min Act: -0.1700
Data Index: 216712 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0932. Min Range: -3.0932
Max Act: 2.9194. Min Act: -0.1700
Data Index: 6600581 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19