Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.9791. Min Act: -0.1700
Data Index: 763285 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.9166. Min Act: -0.1700
Data Index: 8228084 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.8853. Min Act: -0.1700
Data Index: 3453781 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.8384. Min Act: -0.1700
Data Index: 5985084 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7915. Min Act: -0.1700
Data Index: 4546005 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7915. Min Act: -0.1700
Data Index: 4725506 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7915. Min Act: -0.1700
Data Index: 3776672 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7758. Min Act: -0.1700
Data Index: 7629799 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7602. Min Act: -0.1700
Data Index: 6694411 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7758. Min Act: -0.1700
Data Index: 4698152 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7758. Min Act: -0.1700
Data Index: 4187773 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7915. Min Act: -0.1700
Data Index: 5763431 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7758. Min Act: -0.1700
Data Index: 4890963 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7602. Min Act: -0.1700
Data Index: 7523580 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7446. Min Act: -0.1700
Data Index: 2899433 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7446. Min Act: -0.1700
Data Index: 5280398 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7133. Min Act: -0.1700
Data Index: 7918610 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7289. Min Act: -0.1700
Data Index: 1588399 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7289. Min Act: -0.1700
Data Index: 5806599 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9791. Min Range: -3.9791
Max Act: 3.7289. Min Act: -0.1700
Data Index: 4500492 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19