Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5078 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3833. Min Range: -7.3833
Max Act: 7.3833. Min Act: -0.1700
Data Index: 170640 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.9771. Min Act: -0.1700
Data Index: 1731952 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.8833. Min Act: -0.1700
Data Index: 5329994 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.8833. Min Act: -0.1700
Data Index: 6927476 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.7896. Min Act: -0.1700
Data Index: 4674522 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.8208. Min Act: -0.1700
Data Index: 2982360 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.7896. Min Act: -0.1700
Data Index: 3637113 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.7583. Min Act: -0.1700
Data Index: 7446868 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.7583. Min Act: -0.1700
Data Index: 5914992 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.7583. Min Act: -0.1700
Data Index: 375961 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.6958. Min Act: -0.1700
Data Index: 3733975 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.6646. Min Act: -0.1700
Data Index: 6027907 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.6646. Min Act: -0.1700
Data Index: 5179268 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.6646. Min Act: -0.1700
Data Index: 3401569 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.6333. Min Act: -0.1700
Data Index: 1822911 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.6646. Min Act: -0.1700
Data Index: 2664470 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.6333. Min Act: -0.1700
Data Index: 3152435 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.6021. Min Act: -0.1700
Data Index: 1386693 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.6021. Min Act: -0.1700
Data Index: 4516691 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3833. Min Range: -7.3833
Max Act: 6.6021. Min Act: -0.1700
Data Index: 1703663 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19