Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.8989. Min Act: -0.1700
Data Index: 3640911 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.8052. Min Act: -0.1700
Data Index: 8650443 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.7739. Min Act: -0.1700
Data Index: 7206368 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.7427. Min Act: -0.1700
Data Index: 2653739 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.6802. Min Act: -0.1700
Data Index: 5239950 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.6489. Min Act: -0.1700
Data Index: 2805070 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.6489. Min Act: -0.1700
Data Index: 4856550 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.6489. Min Act: -0.1700
Data Index: 5065460 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.5864. Min Act: -0.1700
Data Index: 5652603 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.5552. Min Act: -0.1700
Data Index: 3664840 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.5552. Min Act: -0.1700
Data Index: 7641460 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.5552. Min Act: -0.1700
Data Index: 3146590 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.5239. Min Act: -0.1700
Data Index: 5372701 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.5552. Min Act: -0.1700
Data Index: 2341148 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.5552. Min Act: -0.1700
Data Index: 1413687 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.5239. Min Act: -0.1700
Data Index: 6116866 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.5239. Min Act: -0.1700
Data Index: 5570041 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.4927. Min Act: -0.1700
Data Index: 6122465 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.4927. Min Act: -0.1700
Data Index: 5080040 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8989. Min Range: -5.8989
Max Act: 5.4927. Min Act: -0.1700
Data Index: 7133237 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19