Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 775 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3703. Min Range: -8.3703
Max Act: 8.3703. Min Act: -0.1700
Data Index: 336766 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.9953. Min Act: -0.1700
Data Index: 6619444 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.9328. Min Act: -0.1700
Data Index: 4583053 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.8078. Min Act: -0.1700
Data Index: 324181 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.8078. Min Act: -0.1700
Data Index: 3681407 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.8078. Min Act: -0.1700
Data Index: 1460022 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.7453. Min Act: -0.1700
Data Index: 8744191 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.7453. Min Act: -0.1700
Data Index: 5969546 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.7141. Min Act: -0.1700
Data Index: 5528127 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.6828. Min Act: -0.1700
Data Index: 3326193 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.6516. Min Act: -0.1700
Data Index: 3415638 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.6516. Min Act: -0.1700
Data Index: 8727320 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.6203. Min Act: -0.1700
Data Index: 5200575 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.6203. Min Act: -0.1700
Data Index: 2316094 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.6203. Min Act: -0.1700
Data Index: 3280449 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.6203. Min Act: -0.1700
Data Index: 6348531 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.6203. Min Act: -0.1700
Data Index: 3276876 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.5891. Min Act: -0.1700
Data Index: 1661408 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.5578. Min Act: -0.1700
Data Index: 518840 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3703. Min Range: -8.3703
Max Act: 7.5578. Min Act: -0.1700
Data Index: 2451278 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19