Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5270 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0681. Min Range: -8.0681
Max Act: 8.0681. Min Act: -0.1700
Data Index: 2836660 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.9431. Min Act: -0.1700
Data Index: 5834630 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.9431. Min Act: -0.1700
Data Index: 1870395 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.9431. Min Act: -0.1700
Data Index: 2643784 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.9431. Min Act: -0.1700
Data Index: 2493140 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.8181. Min Act: -0.1700
Data Index: 4909928 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.8181. Min Act: -0.1700
Data Index: 3259024 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.7869. Min Act: -0.1700
Data Index: 5777788 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.7556. Min Act: -0.1700
Data Index: 2975517 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.7244. Min Act: -0.1700
Data Index: 4899726 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.6931. Min Act: -0.1700
Data Index: 5336204 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.6931. Min Act: -0.1700
Data Index: 279402 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.7244. Min Act: -0.1700
Data Index: 7204632 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.6619. Min Act: -0.1700
Data Index: 2975518 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.5994. Min Act: -0.1700
Data Index: 5843261 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.5681. Min Act: -0.1700
Data Index: 4794375 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.5681. Min Act: -0.1700
Data Index: 2399667 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.5681. Min Act: -0.1700
Data Index: 8389567 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.5369. Min Act: -0.1700
Data Index: 5763037 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0681. Min Range: -8.0681
Max Act: 7.5369. Min Act: -0.1700
Data Index: 6746166 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19