Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1786 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.5009. Min Act: -0.1700
Data Index: 2008785 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.4696. Min Act: -0.1700
Data Index: 2862218 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.4071. Min Act: -0.1700
Data Index: 8048609 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.2821. Min Act: -0.1700
Data Index: 4549193 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.2509. Min Act: -0.1700
Data Index: 8189425 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.2821. Min Act: -0.1700
Data Index: 6289105 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.2821. Min Act: -0.1700
Data Index: 6911857 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.2196. Min Act: -0.1700
Data Index: 2321921 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.2196. Min Act: -0.1700
Data Index: 1092134 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.2196. Min Act: -0.1700
Data Index: 5067778 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.1884. Min Act: -0.1700
Data Index: 1492496 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.1884. Min Act: -0.1700
Data Index: 7579136 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.1884. Min Act: -0.1700
Data Index: 6289106 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.1571. Min Act: -0.1700
Data Index: 3815098 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.1259. Min Act: -0.1700
Data Index: 739257 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.1259. Min Act: -0.1700
Data Index: 2739342 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.0633. Min Act: -0.1700
Data Index: 3181276 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.0633. Min Act: -0.1700
Data Index: 5359848 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.0946. Min Act: -0.1700
Data Index: 599740 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5009. Min Range: -4.5009
Max Act: 4.0946. Min Act: -0.1700
Data Index: 3605898 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19