Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4632 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.6809. Min Act: -0.1700
Data Index: 1570074 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.6497. Min Act: -0.1700
Data Index: 2448207 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.6340. Min Act: -0.1700
Data Index: 1389130 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.5871. Min Act: -0.1700
Data Index: 4162979 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.5871. Min Act: -0.1700
Data Index: 4868260 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.5401. Min Act: -0.1700
Data Index: 3588591 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.5401. Min Act: -0.1700
Data Index: 3461564 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.5244. Min Act: -0.1700
Data Index: 3208976 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.5244. Min Act: -0.1700
Data Index: 882497 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.5401. Min Act: -0.1700
Data Index: 6576809 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.5244. Min Act: -0.1700
Data Index: 2107760 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.5088. Min Act: -0.1700
Data Index: 389884 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.4931. Min Act: -0.1700
Data Index: 2767593 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.4774. Min Act: -0.1700
Data Index: 4501369 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.4618. Min Act: -0.1700
Data Index: 851786 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.4461. Min Act: -0.1700
Data Index: 7380231 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.4618. Min Act: -0.1700
Data Index: 8795175 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.4304. Min Act: -0.1700
Data Index: 2380557 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.4461. Min Act: -0.1700
Data Index: 6235206 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6809. Min Range: -3.6809
Max Act: 3.4304. Min Act: -0.1700
Data Index: 1774870 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19