Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2779 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.5002. Min Act: -0.1700
Data Index: 473047 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.5002. Min Act: -0.1700
Data Index: 2450856 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.4689. Min Act: -0.1700
Data Index: 1625914 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.4377. Min Act: -0.1700
Data Index: 8238615 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.4064. Min Act: -0.1700
Data Index: 5975580 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3752. Min Act: -0.1700
Data Index: 1581343 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3752. Min Act: -0.1700
Data Index: 3052265 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3752. Min Act: -0.1700
Data Index: 2378599 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3752. Min Act: -0.1700
Data Index: 7235916 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3752. Min Act: -0.1700
Data Index: 5941659 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3439. Min Act: -0.1700
Data Index: 2471347 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3439. Min Act: -0.1700
Data Index: 5579725 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3127. Min Act: -0.1700
Data Index: 1404443 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3127. Min Act: -0.1700
Data Index: 2180005 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3127. Min Act: -0.1700
Data Index: 2161111 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.2814. Min Act: -0.1700
Data Index: 1625918 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.3127. Min Act: -0.1700
Data Index: 3931896 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.2814. Min Act: -0.1700
Data Index: 1817046 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.2814. Min Act: -0.1700
Data Index: 4390425 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5002. Min Range: -5.5002
Max Act: 5.2814. Min Act: -0.1700
Data Index: 2473363 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19