Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3809 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.7029. Min Act: -0.1700
Data Index: 7884036 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.6404. Min Act: -0.1700
Data Index: 70011 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.5779. Min Act: -0.1700
Data Index: 2158541 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.3904. Min Act: -0.1700
Data Index: 8324383 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.2654. Min Act: -0.1700
Data Index: 5858933 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.3279. Min Act: -0.1700
Data Index: 2118970 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.3279. Min Act: -0.1700
Data Index: 3742017 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.3279. Min Act: -0.1700
Data Index: 1035869 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.2654. Min Act: -0.1700
Data Index: 2836263 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.2029. Min Act: -0.1700
Data Index: 7715134 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.2029. Min Act: -0.1700
Data Index: 4838647 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.1404. Min Act: -0.1700
Data Index: 1660842 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.1404. Min Act: -0.1700
Data Index: 3947420 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.1404. Min Act: -0.1700
Data Index: 5032002 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.0779. Min Act: -0.1700
Data Index: 7590695 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.0779. Min Act: -0.1700
Data Index: 2283850 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.0779. Min Act: -0.1700
Data Index: 5720091 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.0779. Min Act: -0.1700
Data Index: 6330945 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.0779. Min Act: -0.1700
Data Index: 5235628 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7029. Min Range: -9.7029
Max Act: 9.0154. Min Act: -0.1700
Data Index: 3407145 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19