Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.5045. Min Act: -0.1700
Data Index: 5511273 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.3795. Min Act: -0.1700
Data Index: 8457519 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.2545. Min Act: -0.1700
Data Index: 2682954 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.1608. Min Act: -0.1700
Data Index: 6336560 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.1920. Min Act: -0.1700
Data Index: 7680642 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.1920. Min Act: -0.1700
Data Index: 7478741 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.1608. Min Act: -0.1700
Data Index: 7344855 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.1295. Min Act: -0.1700
Data Index: 7554814 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.1295. Min Act: -0.1700
Data Index: 4640535 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.1295. Min Act: -0.1700
Data Index: 1177407 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.1295. Min Act: -0.1700
Data Index: 7985540 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.1295. Min Act: -0.1700
Data Index: 5103734 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.0983. Min Act: -0.1700
Data Index: 3914076 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.0983. Min Act: -0.1700
Data Index: 3617699 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.0983. Min Act: -0.1700
Data Index: 6122906 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.0983. Min Act: -0.1700
Data Index: 3914077 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.0983. Min Act: -0.1700
Data Index: 2855397 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.0983. Min Act: -0.1700
Data Index: 5315428 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.0358. Min Act: -0.1700
Data Index: 7530673 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5045. Min Range: -5.5045
Max Act: 5.0983. Min Act: -0.1700
Data Index: 350324 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19