Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3609 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1278. Min Range: -7.1278
Max Act: 7.0966. Min Act: -0.1700
Data Index: 4964677 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1278. Min Range: -7.1278
Max Act: 7.1278. Min Act: -0.1700
Data Index: 6460029 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1278. Min Range: -7.1278
Max Act: 7.0028. Min Act: -0.1700
Data Index: 1675146 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.9716. Min Act: -0.1700
Data Index: 2764646 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.9716. Min Act: -0.1700
Data Index: 7912318 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.9403. Min Act: -0.1700
Data Index: 1745907 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.9403. Min Act: -0.1700
Data Index: 4041558 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.9091. Min Act: -0.1700
Data Index: 1921428 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.9091. Min Act: -0.1700
Data Index: 981288 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.9091. Min Act: -0.1700
Data Index: 1461139 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.9091. Min Act: -0.1700
Data Index: 8191431 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.8778. Min Act: -0.1700
Data Index: 3778042 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.8466. Min Act: -0.1700
Data Index: 6501922 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.8466. Min Act: -0.1700
Data Index: 4251800 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.8153. Min Act: -0.1700
Data Index: 8311064 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.8153. Min Act: -0.1700
Data Index: 8697581 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.7841. Min Act: -0.1700
Data Index: 736132 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.7841. Min Act: -0.1700
Data Index: 6527245 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.7841. Min Act: -0.1700
Data Index: 923540 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1278. Min Range: -7.1278
Max Act: 6.7528. Min Act: -0.1700
Data Index: 4975683 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19