Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3300 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1622. Min Range: -6.1622
Max Act: 6.1622. Min Act: -0.1700
Data Index: 6363247 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1622. Min Range: -6.1622
Max Act: 6.0997. Min Act: -0.1700
Data Index: 523633 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1622. Min Range: -6.1622
Max Act: 6.0372. Min Act: -0.1700
Data Index: 4544813 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1622. Min Range: -6.1622
Max Act: 6.0060. Min Act: -0.1700
Data Index: 3779880 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.9435. Min Act: -0.1700
Data Index: 4454049 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.9122. Min Act: -0.1700
Data Index: 2127214 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.8810. Min Act: -0.1700
Data Index: 7756438 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.7560. Min Act: -0.1700
Data Index: 3358194 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.7247. Min Act: -0.1700
Data Index: 6938227 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6622. Min Act: -0.1700
Data Index: 2023482 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6935. Min Act: -0.1700
Data Index: 5341766 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6622. Min Act: -0.1700
Data Index: 4383802 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6622. Min Act: -0.1700
Data Index: 6525484 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6310. Min Act: -0.1700
Data Index: 8405912 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6310. Min Act: -0.1700
Data Index: 827759 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.5997. Min Act: -0.1700
Data Index: 8535011 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.6622. Min Act: -0.1700
Data Index: 6296333 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.5685. Min Act: -0.1700
Data Index: 4128819 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.5372. Min Act: -0.1700
Data Index: 6281584 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1622. Min Range: -6.1622
Max Act: 5.5060. Min Act: -0.1700
Data Index: 3755725 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19