Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.6989. Min Act: -0.1700
Data Index: 8658240 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.5739. Min Act: -0.1700
Data Index: 5966303 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.5739. Min Act: -0.1700
Data Index: 3892290 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.5114. Min Act: -0.1700
Data Index: 7060645 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.5114. Min Act: -0.1700
Data Index: 1593787 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.2614. Min Act: -0.1700
Data Index: 5611307 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.1989. Min Act: -0.1700
Data Index: 5719851 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.1364. Min Act: -0.1700
Data Index: 3700602 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.1364. Min Act: -0.1700
Data Index: 5234072 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.1989. Min Act: -0.1700
Data Index: 4835367 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.1364. Min Act: -0.1700
Data Index: 3207598 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.0739. Min Act: -0.1700
Data Index: 1295003 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.0739. Min Act: -0.1700
Data Index: 2413666 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.0114. Min Act: -0.1700
Data Index: 3313439 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6989. Min Range: -8.6989
Max Act: 8.0114. Min Act: -0.1700
Data Index: 8064721 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6989. Min Range: -8.6989
Max Act: 7.9489. Min Act: -0.1700
Data Index: 186411 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6989. Min Range: -8.6989
Max Act: 7.9489. Min Act: -0.1700
Data Index: 3138512 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6989. Min Range: -8.6989
Max Act: 7.9489. Min Act: -0.1700
Data Index: 1354619 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6989. Min Range: -8.6989
Max Act: 7.9489. Min Act: -0.1700
Data Index: 2462553 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6989. Min Range: -8.6989
Max Act: 7.8551. Min Act: -0.1700
Data Index: 3017475 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19