Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5906 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4032. Min Range: -7.4032
Max Act: 7.4032. Min Act: -0.1700
Data Index: 1303206 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4032. Min Range: -7.4032
Max Act: 7.0907. Min Act: -0.1700
Data Index: 1421397 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4032. Min Range: -7.4032
Max Act: 7.0907. Min Act: -0.1700
Data Index: 7457067 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4032. Min Range: -7.4032
Max Act: 7.0907. Min Act: -0.1700
Data Index: 3897714 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4032. Min Range: -7.4032
Max Act: 7.1220. Min Act: -0.1700
Data Index: 2142739 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.9345. Min Act: -0.1700
Data Index: 679592 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.9345. Min Act: -0.1700
Data Index: 540046 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.9345. Min Act: -0.1700
Data Index: 5342527 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.9032. Min Act: -0.1700
Data Index: 6787070 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.9032. Min Act: -0.1700
Data Index: 6611935 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.9032. Min Act: -0.1700
Data Index: 2897525 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.8720. Min Act: -0.1700
Data Index: 8167512 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.8407. Min Act: -0.1700
Data Index: 5790840 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.8407. Min Act: -0.1700
Data Index: 4916063 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.8720. Min Act: -0.1700
Data Index: 4786546 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.8407. Min Act: -0.1700
Data Index: 7281811 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.8407. Min Act: -0.1700
Data Index: 6611512 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.8095. Min Act: -0.1700
Data Index: 5551752 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.8095. Min Act: -0.1700
Data Index: 5267870 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4032. Min Range: -7.4032
Max Act: 6.7782. Min Act: -0.1700
Data Index: 5979781 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19