Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4021 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0486. Min Range: -6.0486
Max Act: 6.0486. Min Act: -0.1700
Data Index: 3965440 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.7361. Min Act: -0.1700
Data Index: 4341212 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.7049. Min Act: -0.1700
Data Index: 7466585 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.6736. Min Act: -0.1700
Data Index: 3495503 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.6424. Min Act: -0.1700
Data Index: 6452499 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.6111. Min Act: -0.1700
Data Index: 1609363 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.5799. Min Act: -0.1700
Data Index: 7015346 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.5799. Min Act: -0.1700
Data Index: 7061082 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.6111. Min Act: -0.1700
Data Index: 3072363 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.5486. Min Act: -0.1700
Data Index: 167750 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.5486. Min Act: -0.1700
Data Index: 8481264 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.4861. Min Act: -0.1700
Data Index: 2959145 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.4861. Min Act: -0.1698
Data Index: 4990631 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.5174. Min Act: -0.1700
Data Index: 718975 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.4861. Min Act: -0.1700
Data Index: 454521 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.4861. Min Act: -0.1700
Data Index: 3837373 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.4549. Min Act: -0.1700
Data Index: 803148 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.4549. Min Act: -0.1700
Data Index: 6407062 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.4861. Min Act: -0.1699
Data Index: 1091233 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0486. Min Range: -6.0486
Max Act: 5.4236. Min Act: -0.1700
Data Index: 5472676 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19