Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.8523. Min Act: -0.1700
Data Index: 5351037 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.8211. Min Act: -0.1700
Data Index: 1096902 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.7898. Min Act: -0.1700
Data Index: 4562572 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.7898. Min Act: -0.1700
Data Index: 6774115 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.7585. Min Act: -0.1700
Data Index: 4720855 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.7585. Min Act: -0.1700
Data Index: 5549691 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.7585. Min Act: -0.1700
Data Index: 1671419 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.7272. Min Act: -0.1700
Data Index: 2244309 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.7585. Min Act: -0.1700
Data Index: 8592534 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6959. Min Act: -0.1700
Data Index: 8174944 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6959. Min Act: -0.1700
Data Index: 3738344 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6959. Min Act: -0.1700
Data Index: 639905 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6959. Min Act: -0.1700
Data Index: 8707017 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6959. Min Act: -0.1700
Data Index: 1609122 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6959. Min Act: -0.1700
Data Index: 8410153 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6646. Min Act: -0.1700
Data Index: 207208 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6646. Min Act: -0.1700
Data Index: 1667964 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6646. Min Act: -0.1700
Data Index: 4443398 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6646. Min Act: -0.1700
Data Index: 5838763 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.6646. Min Act: -0.1700
Data Index: 6238739 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19