Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2471 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.7734. Min Act: -0.1700
Data Index: 1721898 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.7422. Min Act: -0.1700
Data Index: 8350925 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.7422. Min Act: -0.1700
Data Index: 407211 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.6797. Min Act: -0.1700
Data Index: 6761976 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.6797. Min Act: -0.1700
Data Index: 3947273 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.6484. Min Act: -0.1700
Data Index: 6069253 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.6172. Min Act: -0.1700
Data Index: 5192949 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5859. Min Act: -0.1700
Data Index: 6979495 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.6172. Min Act: -0.1700
Data Index: 2754475 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.6172. Min Act: -0.1700
Data Index: 464905 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5859. Min Act: -0.1700
Data Index: 2023458 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5859. Min Act: -0.1700
Data Index: 5278483 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5859. Min Act: -0.1700
Data Index: 1224058 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5547. Min Act: -0.1700
Data Index: 5326021 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5547. Min Act: -0.1700
Data Index: 752233 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5547. Min Act: -0.1700
Data Index: 8086831 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5547. Min Act: -0.1700
Data Index: 1791939 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5859. Min Act: -0.1700
Data Index: 3433242 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5547. Min Act: -0.1700
Data Index: 4509012 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7734. Min Range: -5.7734
Max Act: 5.5547. Min Act: -0.1700
Data Index: 101195 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19