Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4744 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.3741. Min Act: -0.1696
Data Index: 7347755 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.3116. Min Act: -0.1700
Data Index: 5968184 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.2491. Min Act: -0.1700
Data Index: 4967180 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1866. Min Act: -0.1699
Data Index: 3177258 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1866. Min Act: -0.1700
Data Index: 1920197 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1866. Min Act: -0.1696
Data Index: 2800111 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1866. Min Act: -0.1700
Data Index: 7605451 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1866. Min Act: -0.1700
Data Index: 1251127 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1866. Min Act: -0.1700
Data Index: 731383 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1866. Min Act: -0.1700
Data Index: 5941653 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1866. Min Act: -0.1700
Data Index: 3963242 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1866. Min Act: -0.1700
Data Index: 5327861 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1866. Min Act: -0.1700
Data Index: 638137 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1241. Min Act: -0.1697
Data Index: 113099 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1241. Min Act: -0.1700
Data Index: 6832360 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1241. Min Act: -0.1700
Data Index: 3955224 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.0616. Min Act: -0.1700
Data Index: 69129 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.0616. Min Act: -0.1700
Data Index: 1075779 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.1241. Min Act: -0.1700
Data Index: 4829934 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3741. Min Range: -7.3741
Max Act: 7.0616. Min Act: -0.1700
Data Index: 3022123 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19