Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5890 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.2004. Min Act: -0.1700
Data Index: 3924421 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.1379. Min Act: -0.1700
Data Index: 8793920 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.0441. Min Act: -0.1700
Data Index: 1048886 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9816. Min Act: -0.1700
Data Index: 1979026 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9504. Min Act: -0.1700
Data Index: 7007888 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9504. Min Act: -0.1700
Data Index: 2677824 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9504. Min Act: -0.1700
Data Index: 8614316 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9504. Min Act: -0.1700
Data Index: 3974517 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9504. Min Act: -0.1700
Data Index: 2443467 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9504. Min Act: -0.1700
Data Index: 5474428 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9504. Min Act: -0.1700
Data Index: 3921838 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9504. Min Act: -0.1700
Data Index: 2928819 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9504. Min Act: -0.1700
Data Index: 5316889 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.8879. Min Act: -0.1700
Data Index: 5489498 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.8879. Min Act: -0.1700
Data Index: 3434651 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9191. Min Act: -0.1700
Data Index: 3097676 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.8879. Min Act: -0.1700
Data Index: 2472694 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.8566. Min Act: -0.1700
Data Index: 2003797 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.8566. Min Act: -0.1700
Data Index: 4797946 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.8566. Min Act: -0.1700
Data Index: 41724 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19