Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3153 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0903. Min Range: -11.0903
Max Act: 11.0903. Min Act: -0.1700
Data Index: 3440971 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0903. Min Range: -11.0903
Max Act: 11.0903. Min Act: -0.1700
Data Index: 8781013 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.9653. Min Act: -0.1694
Data Index: 977821 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.9028. Min Act: -0.1700
Data Index: 2695993 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.9028. Min Act: -0.1700
Data Index: 2501778 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.8403. Min Act: -0.1700
Data Index: 3900041 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.8403. Min Act: -0.1700
Data Index: 7296684 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.7778. Min Act: -0.1700
Data Index: 245428 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.7778. Min Act: -0.1700
Data Index: 2710884 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.8403. Min Act: -0.1700
Data Index: 2825592 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.7153. Min Act: -0.1700
Data Index: 75327 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.7153. Min Act: -0.1700
Data Index: 5181831 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.6528. Min Act: -0.1700
Data Index: 8634964 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.7153. Min Act: -0.1700
Data Index: 4871881 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.7153. Min Act: -0.1700
Data Index: 4976428 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.5903. Min Act: -0.1700
Data Index: 4791652 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.6528. Min Act: -0.1700
Data Index: 3900040 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.5903. Min Act: -0.1700
Data Index: 5429938 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.5903. Min Act: -0.1700
Data Index: 1896133 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0903. Min Range: -11.0903
Max Act: 10.5278. Min Act: -0.1700
Data Index: 7298477 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19