Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2390 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1767. Min Act: -0.1700
Data Index: 7618211 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1601. Min Act: -0.1700
Data Index: 3981831 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1434. Min Act: -0.1700
Data Index: 7317507 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1767. Min Act: -0.1700
Data Index: 428971 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1267. Min Act: -0.1700
Data Index: 7618207 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1100. Min Act: -0.1700
Data Index: 6029562 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1100. Min Act: -0.1700
Data Index: 1980760 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1100. Min Act: -0.1700
Data Index: 1518634 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1100. Min Act: -0.1700
Data Index: 2759308 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.1100. Min Act: -0.1700
Data Index: 6882171 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0932. Min Act: -0.1700
Data Index: 2594508 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0932. Min Act: -0.1700
Data Index: 1185855 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0932. Min Act: -0.1700
Data Index: 1766305 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0765. Min Act: -0.1700
Data Index: 1175579 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0765. Min Act: -0.1700
Data Index: 4754296 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0597. Min Act: -0.1700
Data Index: 1176330 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0932. Min Act: -0.1700
Data Index: 5314140 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0765. Min Act: -0.1700
Data Index: 401696 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0597. Min Act: -0.1700
Data Index: 4221323 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1767. Min Range: -2.1767
Max Act: 2.0597. Min Act: -0.1700
Data Index: 4163137 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19