Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1167 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.9972. Min Act: -0.1700
Data Index: 2632647 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.7472. Min Act: -0.1700
Data Index: 248242 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6535. Min Act: -0.1700
Data Index: 8070771 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6847. Min Act: -0.1700
Data Index: 7122831 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.6535. Min Act: -0.1700
Data Index: 1854004 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.5910. Min Act: -0.1700
Data Index: 5431632 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.5285. Min Act: -0.1700
Data Index: 5175669 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.4972. Min Act: -0.1700
Data Index: 8117541 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.4972. Min Act: -0.1700
Data Index: 5473705 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.4660. Min Act: -0.1700
Data Index: 2737791 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.4035. Min Act: -0.1700
Data Index: 1669958 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.3722. Min Act: -0.1700
Data Index: 6465280 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.3722. Min Act: -0.1700
Data Index: 6115178 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.3410. Min Act: -0.1700
Data Index: 8545400 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.3097. Min Act: -0.1700
Data Index: 885781 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.3410. Min Act: -0.1700
Data Index: 130083 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.3410. Min Act: -0.1700
Data Index: 2310305 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.3097. Min Act: -0.1700
Data Index: 6578918 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.3097. Min Act: -0.1700
Data Index: 1434297 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9972. Min Range: -5.9972
Max Act: 5.3097. Min Act: -0.1700
Data Index: 7192972 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19