Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 882 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1148. Min Range: -7.1148
Max Act: 7.1148. Min Act: -0.1700
Data Index: 7171029 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.8648. Min Act: -0.1700
Data Index: 3355023 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.8336. Min Act: -0.1700
Data Index: 5452699 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.8023. Min Act: -0.1700
Data Index: 7282436 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.8023. Min Act: -0.1700
Data Index: 6809059 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.7711. Min Act: -0.1700
Data Index: 8269971 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.7398. Min Act: -0.1700
Data Index: 5894149 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.6461. Min Act: -0.1700
Data Index: 5832821 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.6148. Min Act: -0.1700
Data Index: 343040 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.6148. Min Act: -0.1700
Data Index: 1336288 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.6148. Min Act: -0.1700
Data Index: 8804992 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.5836. Min Act: -0.1700
Data Index: 3161051 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.5523. Min Act: -0.1700
Data Index: 1265890 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.5211. Min Act: -0.1700
Data Index: 5009054 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.5523. Min Act: -0.1700
Data Index: 5262841 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.5211. Min Act: -0.1700
Data Index: 1312486 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.5211. Min Act: -0.1700
Data Index: 7295193 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.4898. Min Act: -0.1700
Data Index: 4797953 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.4273. Min Act: -0.1700
Data Index: 4014281 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1148. Min Range: -7.1148
Max Act: 6.4273. Min Act: -0.1700
Data Index: 6863200 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19