Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1552 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.8204. Min Act: -0.1700
Data Index: 8112291 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.6954. Min Act: -0.1700
Data Index: 7708491 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.6954. Min Act: -0.1700
Data Index: 498415 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.6954. Min Act: -0.1700
Data Index: 7056739 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.6641. Min Act: -0.1700
Data Index: 1963668 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1616272 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.6016. Min Act: -0.1700
Data Index: 7056738 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.6016. Min Act: -0.1700
Data Index: 384292 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.5704. Min Act: -0.1700
Data Index: 1234568 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.6016. Min Act: -0.1700
Data Index: 3103363 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.5391. Min Act: -0.1700
Data Index: 7144266 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.5391. Min Act: -0.1700
Data Index: 7690979 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.4766. Min Act: -0.1700
Data Index: 3404113 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.5079. Min Act: -0.1700
Data Index: 7056741 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.5079. Min Act: -0.1700
Data Index: 7490599 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.5079. Min Act: -0.1700
Data Index: 533417 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.4766. Min Act: -0.1700
Data Index: 1487039 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.4766. Min Act: -0.1700
Data Index: 2824277 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.4766. Min Act: -0.1700
Data Index: 7490615 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8204. Min Range: -5.8204
Max Act: 5.4454. Min Act: -0.1700
Data Index: 7056743 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19