Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3097 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.8177. Min Act: -0.1676
Data Index: 1852653 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.8177. Min Act: -0.1700
Data Index: 3035444 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.8177. Min Act: -0.1699
Data Index: 4406813 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.7551. Min Act: -0.1700
Data Index: 588828 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.7551. Min Act: -0.1691
Data Index: 1280898 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.7551. Min Act: -0.1694
Data Index: 6632155 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.7551. Min Act: -0.1696
Data Index: 5316197 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.7239. Min Act: -0.1691
Data Index: 1218262 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.7239. Min Act: -0.1440
Data Index: 6793450 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.7239. Min Act: -0.1308
Data Index: 2441702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.7239. Min Act: -0.1134
Data Index: 2366137 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.6926. Min Act: -0.1700
Data Index: 3002340 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.6926. Min Act: -0.1684
Data Index: 6970479 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.5674. Min Act: -0.1700
Data Index: 5762351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.5674. Min Act: -0.1315
Data Index: 1177533 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.5674. Min Act: -0.1700
Data Index: 5060816 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.5361. Min Act: -0.1579
Data Index: 7065078 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.4421. Min Act: -0.1698
Data Index: 6046052 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.4421. Min Act: -0.1695
Data Index: 7584983 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8177. Min Range: -3.8177
Max Act: 3.4107. Min Act: -0.1684
Data Index: 761503 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19