Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.4732. Min Act: -0.1700
Data Index: 4077376 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.3170. Min Act: -0.1700
Data Index: 4077359 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.2857. Min Act: -0.1700
Data Index: 4077361 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.1607. Min Act: -0.1700
Data Index: 6710003 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.1607. Min Act: -0.1700
Data Index: 2214625 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.1607. Min Act: -0.1700
Data Index: 4077375 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.1295. Min Act: -0.1700
Data Index: 4730017 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.1295. Min Act: -0.1700
Data Index: 4979622 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.1295. Min Act: -0.1700
Data Index: 8240673 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0982. Min Act: -0.1697
Data Index: 3662594 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0982. Min Act: -0.1700
Data Index: 8388036 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0982. Min Act: -0.1700
Data Index: 4245167 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0670. Min Act: -0.1700
Data Index: 5374126 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0982. Min Act: -0.1700
Data Index: 5391431 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0982. Min Act: -0.1700
Data Index: 3993958 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0982. Min Act: -0.1700
Data Index: 5374125 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0982. Min Act: -0.1700
Data Index: 5591832 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0670. Min Act: -0.1700
Data Index: 7932748 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0670. Min Act: -0.1700
Data Index: 5586273 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4732. Min Range: -5.4732
Max Act: 5.0982. Min Act: -0.1700
Data Index: 4132552 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19