Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.6776. Min Act: -0.1700
Data Index: 8338894 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.4901. Min Act: -0.1700
Data Index: 6878379 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.4901. Min Act: -0.1700
Data Index: 6878377 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.4276. Min Act: -0.1700
Data Index: 371369 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.3651. Min Act: -0.1700
Data Index: 8338895 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.2713. Min Act: -0.1700
Data Index: 4597098 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.3338. Min Act: -0.1700
Data Index: 1770099 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.3026. Min Act: -0.1700
Data Index: 852330 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.2713. Min Act: -0.1700
Data Index: 6852377 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.1776. Min Act: -0.1700
Data Index: 5349413 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.2088. Min Act: -0.1700
Data Index: 3237075 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.2088. Min Act: -0.1700
Data Index: 1733029 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.3026. Min Act: -0.1700
Data Index: 8119213 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.1776. Min Act: -0.1700
Data Index: 8610780 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.0838. Min Act: -0.1700
Data Index: 1770095 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.1151. Min Act: -0.1700
Data Index: 3562422 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.1151. Min Act: -0.1700
Data Index: 5737724 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.1463. Min Act: -0.1700
Data Index: 4554740 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.1151. Min Act: -0.1700
Data Index: 5650501 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6776. Min Range: -8.6776
Max Act: 8.1151. Min Act: -0.1700
Data Index: 6260053 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19