Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0246. Min Range: -6.0246
Max Act: 6.0246. Min Act: -0.1700
Data Index: 6797922 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.9934. Min Act: -0.1700
Data Index: 450095 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.9934. Min Act: -0.1700
Data Index: 2150999 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.9309. Min Act: -0.1700
Data Index: 153890 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.8996. Min Act: -0.1700
Data Index: 709132 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.8996. Min Act: -0.1700
Data Index: 6753548 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.8371. Min Act: -0.1700
Data Index: 4044143 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.8059. Min Act: -0.1700
Data Index: 1313992 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.7746. Min Act: -0.1700
Data Index: 4420430 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.7434. Min Act: -0.1700
Data Index: 1367307 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.7121. Min Act: -0.1700
Data Index: 771218 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.7121. Min Act: -0.1700
Data Index: 1275295 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.7121. Min Act: -0.1700
Data Index: 7816875 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.6809. Min Act: -0.1700
Data Index: 5763181 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.6496. Min Act: -0.1700
Data Index: 3375452 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.6496. Min Act: -0.1700
Data Index: 271758 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.6496. Min Act: -0.1700
Data Index: 861691 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.6496. Min Act: -0.1700
Data Index: 5031825 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.6496. Min Act: -0.1700
Data Index: 391202 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0246. Min Range: -6.0246
Max Act: 5.5871. Min Act: -0.1700
Data Index: 5134500 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19