Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1744 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1752. Min Range: -8.1752
Max Act: 8.1752. Min Act: -0.1700
Data Index: 4088618 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1752. Min Range: -8.1752
Max Act: 8.0502. Min Act: -0.1700
Data Index: 3164343 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.9877. Min Act: -0.1700
Data Index: 2814711 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.8002. Min Act: -0.1700
Data Index: 5997103 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.8002. Min Act: -0.1700
Data Index: 8165102 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.8002. Min Act: -0.1700
Data Index: 7202900 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.7689. Min Act: -0.1700
Data Index: 6659734 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.7689. Min Act: -0.1700
Data Index: 3644683 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.7377. Min Act: -0.1700
Data Index: 8449335 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.6752. Min Act: -0.1700
Data Index: 6971636 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.7064. Min Act: -0.1700
Data Index: 8464118 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.7064. Min Act: -0.1700
Data Index: 4119564 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.6752. Min Act: -0.1700
Data Index: 2092672 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.6752. Min Act: -0.1700
Data Index: 46864 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.6752. Min Act: -0.1700
Data Index: 6369704 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.6439. Min Act: -0.1700
Data Index: 7584539 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.6439. Min Act: -0.1700
Data Index: 6700366 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.6439. Min Act: -0.1700
Data Index: 6431254 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.6439. Min Act: -0.1700
Data Index: 5437146 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1752. Min Range: -8.1752
Max Act: 7.6127. Min Act: -0.1700
Data Index: 4000590 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19