Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3766 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.8692. Min Act: -0.1700
Data Index: 2279878 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.8067. Min Act: -0.1699
Data Index: 7175156 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.7442. Min Act: -0.1696
Data Index: 3943348 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.6817. Min Act: -0.1700
Data Index: 7175151 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.6817. Min Act: -0.1699
Data Index: 7344306 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.5567. Min Act: -0.1700
Data Index: 5092600 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.2442. Min Act: -0.1700
Data Index: 932212 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.2442. Min Act: -0.1700
Data Index: 1660627 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.1817. Min Act: -0.1700
Data Index: 4125485 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.1192. Min Act: -0.1700
Data Index: 1722328 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.1192. Min Act: -0.1700
Data Index: 5398507 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.1192. Min Act: -0.1699
Data Index: 5877292 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8692. Min Range: -12.8692
Max Act: 11.9942. Min Act: -0.1700
Data Index: 6754788 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.0567. Min Act: -0.1700
Data Index: 3496089 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.0567. Min Act: -0.1700
Data Index: 640217 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.0567. Min Act: -0.1700
Data Index: 1265156 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8692. Min Range: -12.8692
Max Act: 11.9942. Min Act: -0.1700
Data Index: 5916922 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8692. Min Range: -12.8692
Max Act: 12.0567. Min Act: -0.1700
Data Index: 5948855 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8692. Min Range: -12.8692
Max Act: 11.9942. Min Act: -0.1700
Data Index: 3808596 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8692. Min Range: -12.8692
Max Act: 11.9317. Min Act: -0.1700
Data Index: 2360063 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19