Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0230. Min Range: -7.0230
Max Act: 7.0230. Min Act: -0.1700
Data Index: 4323253 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.7417. Min Act: -0.1700
Data Index: 5034586 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.7417. Min Act: -0.1700
Data Index: 5517675 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.7105. Min Act: -0.1700
Data Index: 1585446 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.6480. Min Act: -0.1700
Data Index: 2470069 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.6167. Min Act: -0.1700
Data Index: 1616817 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.5230. Min Act: -0.1700
Data Index: 2595119 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.4605. Min Act: -0.1700
Data Index: 5824479 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.4605. Min Act: -0.1700
Data Index: 1175151 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.4917. Min Act: -0.1700
Data Index: 5116732 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.3980. Min Act: -0.1700
Data Index: 6576515 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.3980. Min Act: -0.1700
Data Index: 2942055 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.3667. Min Act: -0.1700
Data Index: 2728239 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.3667. Min Act: -0.1700
Data Index: 6920549 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.3980. Min Act: -0.1700
Data Index: 5504882 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.3042. Min Act: -0.1700
Data Index: 2613229 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.3042. Min Act: -0.1700
Data Index: 1093510 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.2730. Min Act: -0.1700
Data Index: 196407 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.2417. Min Act: -0.1700
Data Index: 4925960 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0230. Min Range: -7.0230
Max Act: 6.2417. Min Act: -0.1700
Data Index: 4121982 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19