Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2028. Min Range: -7.2028
Max Act: 7.2028. Min Act: -0.1700
Data Index: 15570 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.9841. Min Act: -0.1700
Data Index: 7316704 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.8903. Min Act: -0.1700
Data Index: 3766233 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.8591. Min Act: -0.1700
Data Index: 7945847 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.7653. Min Act: -0.1700
Data Index: 103255 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.7341. Min Act: -0.1700
Data Index: 2899527 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.6716. Min Act: -0.1700
Data Index: 2365946 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.6403. Min Act: -0.1700
Data Index: 856014 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.6403. Min Act: -0.1700
Data Index: 3194821 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.6091. Min Act: -0.1700
Data Index: 1020772 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.5466. Min Act: -0.1700
Data Index: 491625 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.5466. Min Act: -0.1700
Data Index: 7483304 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.6091. Min Act: -0.1700
Data Index: 2493028 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.4528. Min Act: -0.1700
Data Index: 5559993 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.4841. Min Act: -0.1700
Data Index: 3534279 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.4528. Min Act: -0.1700
Data Index: 1888043 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.4216. Min Act: -0.1700
Data Index: 6098380 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.4216. Min Act: -0.1700
Data Index: 571623 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.4841. Min Act: -0.1700
Data Index: 6684959 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2028. Min Range: -7.2028
Max Act: 6.4216. Min Act: -0.1700
Data Index: 1776572 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19