Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.7048. Min Act: -0.1700
Data Index: 8253118 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.6423. Min Act: -0.1700
Data Index: 5017197 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.6111. Min Act: -0.1700
Data Index: 4239063 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.5798. Min Act: -0.1700
Data Index: 4895250 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.5173. Min Act: -0.1700
Data Index: 8471882 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.5173. Min Act: -0.1700
Data Index: 4320696 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4861. Min Act: -0.1700
Data Index: 8155790 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4548. Min Act: -0.1700
Data Index: 6357702 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4548. Min Act: -0.1700
Data Index: 880268 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4548. Min Act: -0.1700
Data Index: 897838 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4548. Min Act: -0.1700
Data Index: 6962563 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4548. Min Act: -0.1700
Data Index: 2623416 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4548. Min Act: -0.1700
Data Index: 1889361 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4548. Min Act: -0.1700
Data Index: 235747 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4548. Min Act: -0.1700
Data Index: 8784846 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4236. Min Act: -0.1700
Data Index: 7876199 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.4236. Min Act: -0.1700
Data Index: 7934080 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.3923. Min Act: -0.1700
Data Index: 5960457 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.3923. Min Act: -0.1700
Data Index: 6748660 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7048. Min Range: -4.7048
Max Act: 4.3611. Min Act: -0.1700
Data Index: 324106 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19